Semantic Kernel

framework

AI 辅助整理 · 事实字段按公开来源校验

微软的 LLM 编排 SDK，面向企业与多语言，将提示、插件与规划器组合进现有应用。

内容完整度： 4/5 · 待补：related_entities

事实字段

定位

LLM 编排 SDK

主语言

C#/Python/Java

开发方

Microsoft

许可证

MIT

来源追溯： 事实字段来自公开来源整理；字段级来源元数据待继续补齐，无法稳定核验的信息不做臆测。

整理说明

本页围绕「定位、事实字段、演进时间线、关联动态」组织信息，方便快速判断 Semantic Kernel 在 AI Agent 与大模型生态中的位置。

事实型字段保持保守：未公开或无法稳定核验的信息不做臆测；关联动态保留原始来源链接，便于继续阅读。

版本演进

2026-07-08

update

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech

2026-07-08

update

Reward-Density Heuristic for Dynamic Multi-Vehicle Routing: Performance and Computational Efficiency

2026-07-08

update

Prompt Coach: An Empirical Evaluation of an Agentic Tutor for Learning Prompt Engineering in Software Development

2026-07-08

update

Scalable Perturbation Learning for Online Self-Supervised Echo State Networks

2026-07-08

update

Modeling Normal Is All You Need: Joint Latent Clustering for Anomaly Detection in Multimodal Cyber-Physical Systems

2026-07-08

update

PVCap: Towards Accurate 3D Dense Captioning via PseudoCap and VoxelCapNet

2026-07-08

update

Agents That Teach: Towards Designing Incidental Learning Back into AI-Assisted Software Development

2026-07-08

update

EcoVision: AI-Powered Drone Imaging for Salt Marsh Vegetation Monitoring and Dominance Mapping

2026-07-08

update

LLM-Guided Measurement Credibility Correction for Trustworthy Industrial Process Inference

2026-07-08

update

X-FEMR: A Token-level Explainable Approach for Electronic Health Records Foundation Models using Transformer-based Models

2026-07-08

update

TriA Pipeline: A Large-Scale Automatic Audio Annotation Pipeline For Audio Classification In Specific Scenarios

2026-07-08

update

Pluralis v0.1: Towards a Multicultural, Multimodal, Multilingual Benchmark for AI Risk and Reliability

2026-07-08

update

A toy framework for single and multi-agent human-AI curiosity ecosystems

2026-07-08

update

Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents

2026-07-08

update

Canopy: A Heterograph Foundation Model for Metabolic Engineering

2026-07-08

update

Task Decomposition-Guided Reranking for Adaptive Agent Skill Retrieval

2026-07-08

update

From Sinhala to Dhivehi: Cross-Lingual Transfer Learning for Low-Resource Speech Recognition

2026-07-08

update

Token-Based Dual-view Fusion and Adaptation of Large Vision Models for Breast Cancer Classification

2026-07-08

update

DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail

2026-07-08

update

Driving the Wrong Way: Leveraging Interpretability in End2End Autonomous Driving Models

2026-07-08

update

Responsible Personalisation: The Double-Edged Sword of Personalisation in Human-Robot Interaction

2026-07-08

update

TopoBrick: Agentic Topology Sampling of Exogenous Variables for Zero-Shot Building IoT Forecasting

2026-07-08

update

Automated Compliance Mapping in Cloud Security with Domain-Adapted Sentence Transformers

2026-07-08

update

Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement

2026-07-08

update

A Function-Space Dichotomy for Compositional Learning: Exponential Sub-Optimality of the Neural Tangent Kernel

2026-07-08

update

What Images Cannot Say: Language-Guided Olfactory Representation Learning

2026-07-08

update

Analysis-by-Proxy: Localization Signals in VLMs Operating as Condition Encoders

2026-07-08

update

From Voting to Agent Collaboration: Answer-Type-Aware LLM Pipelines for BioASQ 14b

2026-07-08

update

WordVoice: Explicit and Decoupled Multi-Dimensional Word-Level Control for LLM-Based TTS

2026-07-08

update

Provable learning separation for predicting time-evolution of quantum many-body systems

2026-07-08

update

Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities

2026-07-08

update

AirflowAttack: Thermal-Airflow Adversarial Perturbations against Infrared Remote-Sensing Vision-Language Models

2026-07-08

update

Pitwall: Faithful Natural-Language Race-Strategy Briefings from a Calibrated Real-Time Monte Carlo Engine

2026-07-08

update

FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference

2026-07-08

update

Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment

2026-07-08

update

Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion

2026-07-07

update

Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenses

2026-07-07

update

Multi-Large Language Model Orchestrated Severity Assessment of Clinical Records (MOSAIC)

2026-07-07

update

RUFNet: Query-Guided Support Mask Refinement and Uncertainty Fusion based on Hybrid Mamba for Few-Shot Brain Tumor Segmentation

2026-07-07

update

CollabEval: Statistically Efficient Collaborative Model Evaluation via Matrix Completion

2026-07-07

update

Toward Trustworthy Large Language Model Agents in Healthcare

2026-07-07

update

Diffusion-Guided Uncertainty-Aware Delayed Policy Optimization

2026-07-07

update

Computing Monetary Risk Measures in Linear Time

2026-07-07

update

AIFS-SUBS: Extending Data-Driven Forecasting to Sub-Seasonal Timescales

2026-07-07

update

Choosing a parallel heterogeneous ensemble method for tabular classification

2026-07-07

update

Grokking Is Conditional and Fragile: A Fully-Tractable, Multi-Seed Study at 12K Parameters

2026-07-07

update

Rating the Pitch, Not the Product: User Evaluations of LLMs Reflect Expectations More Than Performance

2026-07-07

update

Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing

2026-07-07

update

PDEFlow: Autonomous Agentic PDE Pipelines for Neural Operator Learning and Solver-Free Inference

2026-07-07

update

EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments

2026-07-07

update

ClassicLogic: A Knowledge-Driven Benchmark of Classic Puzzle Games for Evaluating Compositional Generalization

2026-07-07

update

Latent Programming Horizons in Coding Agents

2026-07-07

update

Noisy-Channel Minimum Bayes Risk Decoding

2026-07-07

update

EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer

2026-07-07

update

Probing Geospatial SSL Representations with Environmental Signals

2026-07-07

update

Video-based detection of cessation of breathing in pre-term infants using machine learning

2026-07-07

update

MoP-JEPA: Hard-Assigned Predictor Mixtures for Stochastic JEPA World Models

2026-07-07

update

Streaming Neural Speech Codecs through Time-Invariant Representations

2026-07-07

update

FUSE: FK-Steered Multi-Modal Flow Matching for Efficient Simulation-Based Posterior Estimation

2026-07-07

update

SalAngaBhava: A Sinhala Market Dataset for Aspect-based Sentiment Analysis

2026-07-07

update

Target-Guided Selective Reweighting for Physics-Informed Neural Network Inverse Problems: A Transfer Learning Approach

2026-07-07

update

Untrusted Content Masking for Web Agents with Security Guarantees

2026-07-07

update

MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution

2026-07-07

update

Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning

2026-07-07

update

Biologically Informed Deep Neural Networks for Multi-Omic Integration, Pathway Activity Inference and Risk Stratification in Cancer

2026-07-07

update

Quantum Spectral Anomaly Detection

2026-07-07

update

Evaluating and Understanding Model Editing for Medical Vision Language Models

2026-07-07

update

How Much is Left? LLMs Linearly Encode Their Remaining Output Length

2026-07-07

update

How Far is Too Far? Defining the Distance Threshold for Verification Siamese Networks

2026-07-07

update

OptiAgent: End-to-End Optimization Modeling via Multi-Agent Iterative Refinement

2026-07-07

update

SovereignPA-Bench: Evaluating User-Owned Personal Agents under Evolving Intent, Platform Mediation, and Consent Constraints

2026-07-07

update

GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks

2026-07-07

update

Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation

2026-07-07

update

TabPack: Efficient Hyperparameter Ensembles for Tabular Deep Learning

2026-07-07

update

What Does a Discrete Diffusion Model Learn?

2026-07-07

update

From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model

2026-07-07

update

Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling

2026-07-07

update

AI Wizards at EXIST 2026: Hierarchical Soft-Label Learning for Multimodal Sexism Identification in Memes

2026-07-07

update

Environmental Drivers of Respiratory Disease: A District Level Analysis

2026-07-07

update

Transferability Between Understanding and Generation in Unified Multimodal Models

2026-07-07

update

UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning

2026-07-07

update

dOPSD: On-Policy Self-Distillation for Diffusion Language Models

2026-07-07

update

evalci: A Python Library for Statistically Rigorous Comparison of Language Model Evaluations

2026-07-07

update

Uncertainty-Aware Abstention in Large Language Models with Provable Alignment Guarantees

2026-07-07

update

RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies

2026-07-07

update

ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes

2026-07-07

update

Operator-on-F complements value-equivalence: a planning-time diagnostic for latent world models

2026-07-07

update

Don't Commit Alone: Joint Token Commitment in Diffusion Large Language Models

2026-07-07

update

Regime-Conditional Stabilisation of LLM-Augmented Cooperative Multi-Agent Reinforcement Learning

2026-07-07

update

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders

2026-07-07

update

From Interaction to Intent: Inferring User Objectives from Provenance Logs

2026-07-07

update

VLA Grounder: Language-Conditioning Space Optimization for Black-Box VLA Models

2026-07-07

update

Beyond travel mode: urban context shapes active mobility's mental health effects over time

2026-07-07

update

Training-Free Model Selection and Domain-Aware Score Calibration for First-Shot Anomalous Sound Detection

2026-07-07

update

Measuring Harness-Induced Belief Divergence in Multi-Step LLM Agents

2026-07-07

update

Mechanism-level routing failure in LLMs over Lean-verified algebraic structures

2026-07-07

update

CRISP: A Spatiotemporal Camera-Radar Backbone for Driving via Forecasting-Based World-Model Pretraining

2026-07-07

update

Auto: The AGI Compiler

2026-07-07

update

Mask2Real-WM: Segmentation Masks as a Sim-to-Real Bridge for Controllable Dexterous World Models

2026-07-07

update

Explainable Novel Category Discovery in Semantic Concept Space

2026-07-07

update

MTEB-PT: A Text Embedding Benchmark for Brazilian Portuguese

2026-07-07

update

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models

2026-07-07

update

LCPNet: Latent Consistent Proximal Unfolding Network for Infrared Small Target Detection

2026-07-07

update

G2VD: Generalizable AI-Generated Video Detection via Counterfactual Intervention and Causal Disentanglement

2026-07-07

update

SILO: Simulation-in-the-Loop Sim-to-Real Transfer for Multi-Stage Cable Routing

2026-07-07

update

Machine Learning for Depression Screening and Intervention: an Original Circadian Rhythm Score-based Methodology

2026-07-07

update

GlaKG: A Biomarker-Centric Fundus Knowledge Graph for Explainable Glaucoma Diagnosis and Risk Assessment

2026-07-07

update

URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment

2026-07-07

update

PAST-TIDE: Prototype-Anchored Statement Tuning with Topic-Invariant Normalization for Stance Detection

2026-07-06

update

yetone/native-feel-skill：An Agent Skill for designing cross-platform desktop apps that feel native — distilled from Raycast's 2.0 deep-dive and reverse engineering of Raycast Beta.app. Eight architectural tenets, four-layer architecture, WebKit/WebView2 survival guide, 75-item ship audit.

2026-07-04

update

rpamis/comet：Comet: agent skill harness phase-guarded automation from idea to archive

2026-07-04

update

Show HN: TaskPeace – a task queue my AI coding agents pull work from over MCP

2026-07-03

update

Coding-agents can replicate scientific machine learning papers

2026-07-03

update

Probing Chemical Language Models: Effects of Pre-training and Fine-tuning

2026-07-03

update

Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space

2026-07-03

update

Bayesian Sparse Low-Rank Adaptation for Large Language Model Uncertainty Estimation

2026-07-03

update

RadiomicNet: A Hybrid Radiomics-Guided Lightweight Architecture for Interpretable Medical Image Segmentation

2026-07-03

update

UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development

2026-07-03

update

An Optimisation Framework for the Well-Conditioned Training of Physics-Informed Neural Networks

2026-07-03

update

Overview of Risk Assessment and Management for Intelligent Systems under the AI Act and Beyond

2026-07-03

update

The Eticas AI Risk Taxonomy: Open Infrastructure for Operationalizing AI Audits

2026-07-03

update

Prediction Sets for Counterfactual Decisions: Coverage, Optimality, and Conformal Prediction

2026-07-03

update

Criticality-Based Guard Rail Validation for AI Agent Decisions in Autonomous Telecom Networks

2026-07-03

update

An Additive MLP-GNN Framework for Characterizing Chemical and Structural Contributions to Aqueous Solubility

2026-07-03

update

Aggregation with Exponential Weights is Optimal in Expectation

2026-07-03

update

AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents

2026-07-03

update

HERMES: A Multi-Granularity Labeling Substrate for Pre-training Data Mixtures

2026-07-03

update

Dendritic In-Context Learning in a Single-Layer Spiking Neural Network

2026-07-03

update

Grounded autonomous research: a fault-tolerant LLM pipeline from corpus to manuscript in frontier computational physics

2026-07-03

update

SelectTSL: Prompt-Guided Selective Target Sound Localization in Complex Scenarios

2026-07-03

update

SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces

2026-07-03

update

GAP-GDRNet: Geometry-Aware Monocular Visual Pose Sensing on a Single-Target Synthetic Spacecraft Dataset

2026-07-03

update

Stable Self-Modulating Quantum Fast-Weight Programmers with Bounded Memory Gates

2026-07-03

update

VisionAId: An Offline-First Multimodal Android Assistant for People with Visual Impairment, Featuring Personalized Object Retrieval

2026-07-03

update

Know Your Source: A Public Knowledge Store for Media Background Checks

2026-07-03

update

Bringing Agentic Search to Earth Observation Data Discovery

2026-07-03

update

Steerability via constraints: a substrate for scalable oversight of coding agents

2026-07-03

update

ACID: Action Consistency via Inverse Dynamics for Planning with World Models

2026-07-03

update

Object-centric LeJEPA

2026-07-03

update

Q-GAIN: A Python Package for Machine Learning and Physically Informed Analysis Applications

2026-07-03

update

The Future of NLP may not be at NLP Conferences: Scholarly Migration Patterns in Natural Language Processing

2026-07-03

update

Neuron-Aware Active Few-Shot Learning for LLMs

2026-07-03

update

WorldSample: Closed-loop Real-robot RL with World Modelling

2026-07-03

update

Extreme Adaptive Transformer for Time Series Forecasting

2026-07-03

update

Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data

2026-07-03

update

Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation

2026-07-03

update

Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs

2026-07-03

update

Visually Grounded Self-Reflection for Vision-Language Models via Reinforcement Learning

2026-07-03

update

Controllable Sim Agents with Behavior Latents

2026-07-03

update

Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas

2026-07-03

update

What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates

2026-07-03

update

Online Safety Monitoring for LLMs

2026-07-03

update

LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning

2026-07-03

update

Show HN: QUALITY.md – open format/specification, agent skill, and CLI

2026-07-02

update

Show HN: Mail Memories – A desktop app to rescue photos from Gmail

2026-07-02

update

MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment

2026-07-02

update

CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models

2026-07-02

update

Dynamic Bidirectional Pattern Memory: A Production-Scale Empirical Characterisation of Inference-Time Gating in Clinical NLP

2026-07-02

update

MultiSynt/MT: Trillion-Token Multi-Parallel Pre-Training Data Translated Across 36 Languages

2026-07-02

update

Human-Machine Collaboration on Generative Meta-Learning: Model and Algorithm

2026-07-02

update

Persona Non Grata: LLM Persona-Driven Generations in MCQA are Unstable in Distinct Dimensions

2026-07-02

update

Aionoscope: Debugging Latent-State Accessibility in Time-Series Representations

2026-07-02

update

Bridging Quantum Computing Paradigms toward Semiconductor Yield: A Controlled CV-versus-DV Comparison on Wafer-Map Defect Classification

2026-07-02

update

TRCGL-Net: A Long-Tailed Multi-Label Chest X-Ray Classification Framework with Generative Data Augmentation and Label Co-Occurrence Modeling

2026-07-02

update

Foundation Models vs. Radiomics for Lung Computed Tomography: A Benchmark of Feature Extractors, Classification Heads, and Segmentation Choices

2026-07-02

update

Understanding Large Language Models

2026-07-02

update

Evidence-Supported Credit Risk Report Generation Using News-Centric Financial Knowledge Graphs

2026-07-02

update

Behavior-Adaptive Conversational Agents: Toward a Fluid Personality Framework

2026-07-02

update

EchoRisk: A Multicentre Echocardiography Dataset and Benchmark for Cardio-Oncology

2026-07-02

update

Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates

2026-07-02

update

GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache

2026-07-02

update

MemSyco-Bench: Benchmarking Sycophancy in Agent Memory

2026-07-02

update

Message Passing Enables Efficient Reasoning

2026-07-02

update

Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization

2026-07-02

update

Group-invariant Coresets for Data-efficient Active Learning

2026-07-02

update

SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore Profiles

2026-07-02

update

FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement

2026-07-02

update

GAIA: Geometry-Adaptive Operator Learning for Forward and Inverse Problems

2026-07-02

update

Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search

2026-07-02

update

A Lightweight Self-Supervised Learning Framework for Multivariate Time Series using Hierarchical-JEPA on ECG Data

2026-07-02

update

Adversarial Pragmatics for AI Safety Evaluation: A Benchmark for Instruction Conflict, Embedded Commands, and Policy Ambiguity

2026-07-02

update

Diffusion-GR2: Diffusion Generative Reasoning Re-ranker

2026-07-02

update

Decision-Aware Training for Sample-Based Generative Models

2026-07-02

update

Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations

2026-07-02

update

Optimal Resource Utilization for Autonomous Laboratory Orchestrators

2026-07-02

update

Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?

2026-07-02

update

FurnitureVLA: Learning Long-Horizon Bimanual Furniture Assembly with Vision-Language-Action Model

2026-07-02

update

The State-Prediction Separation Hypothesis

2026-07-02

update

Language-Critique Imitation Learning from Suboptimal Demonstrations

2026-07-02

update

Measuring the Gap Between Human and LLM Research Ideas

2026-07-02

update

Show HN: AnalystAIPack – 118 runnable agent skills for malware analysis and RE

2026-07-01

update

cloudflare/security-audit-skill：A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings

2026-07-01

update

When to Truncate a Feature Ranking: A Residual-Overlap Stopping Rule for Subset Selection

2026-07-01

update

Overview of the TalentCLEF 2026: Skill and Job Title Intelligence for Human Capital Management

2026-07-01

update

ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping

2026-07-01

update

Diffusing Blame: Task-Dependent Credit Assignment in Biologically Plausible Dual-Stream Networks

2026-07-01

update

Nonlinearity-Aware LoRA: Structured Gate Adaptation under Low-Rank Constraints

2026-07-01

update

Cross-lingual Relation Extraction with Large Language Models: Zero-Shot, Few-Shot, and Fine-Tuned Evaluation on Romanian

2026-07-01

update

STEB: Style Text Embedding Benchmark

2026-07-01

update

JL1-CC&QA: Extending the JL1-CD Benchmark with Change Captioning and Question Answering

2026-07-01

update

A Self-Evolving Agentic System for Automated Generation and Execution of Biological Protocols

2026-07-01

update

Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers

2026-07-01

update

SpikeLogBERT: Energy-Efficient Log Parsing Using Spiking Transformer Networks

2026-07-01

update

CHERRY: Compressed Hierarchical Experts with Recurrent Representational Yield

2026-07-01

update

Evo-PI: Aligning Medical Reasoning via Evolving Principle-Guided Supervision

2026-07-01

update

Relational and Sequential Conformal Inference for Energy Time Series over Graphs via Foundation Models

2026-07-01

update

Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models

2026-07-01

update

Low-dimensional topology of deep neural networks

2026-07-01

update

Accelerating Conformal Prediction via Approximate Leave-One-Out

2026-07-01

update

Semantic Leakage and Privacy Preservation in Relay-Assisted Semantic Communications

2026-07-01

update

TreeAgent: A Generalizable Multi-Agent Framework for Automated Bias Labeling in Forestry via Compiled Expert Rules and Vision-Language Models

2026-07-01

update

DigitalCoach: Communication and Grounding Gaps in Human and Agentic Computer Use Coaching

2026-07-01

update

Radial Suppression Accelerates Algorithmic Generalization: A Geometric Analysis of Delayed Generalization

2026-07-01

update

Self-Study Reconsidered: The Hidden Fragility of Learning from Self-Generated QA

2026-07-01

update

CoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty Estimation

2026-07-01

update

Scalable Behaviour Cloning on Browser Using via Skill Distillation

2026-07-01

update

FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning

2026-07-01

update

Automated Background Swapping for Robustness against Spurious Backgrounds

2026-07-01

update

SemRF: A Semantic Reference Frame for Residual-Stream Dynamics in Language Models

2026-07-01

update

Generative Skill Composition for LLM Agents

2026-07-01

update

AdaJEPA: An Adaptive Latent World Model

2026-07-01

update

Freeform Preference Learning for Robotic Manipulation

2026-07-01

update

When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors

2026-07-01

update

Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs

2026-07-01

update

Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision

2026-07-01

update

Spatial Reasoning via Modality Switching Between Language and Symbolic Representation

2026-07-01

update

From Idea to Prototype in an Afternoon: Scaffolded, AI-Assisted Rapid VA Prototyping

2026-07-01

update

Safe Online Learning via Smooth Safety-Structured Policy Composition

2026-07-01

update

PGUDA: Pressure-Guided Unsupervised Domain Adaptation with Cross-Modal Knowledge Distillation for sEMG-Based Gesture Recognition

2026-07-01

update

Dualformer: Efficient Feature Extractor for Complex-valued Blind Communication Signal Analysis

2026-07-01

update

Stage-Transition Dense Reward Modeling for Reinforcement Learning

2026-07-01

update

ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents

2026-07-01

update

World-Model Collapse as a Phase Transition

2026-07-01

update

Xiaomi-GUI-0 Technical Report

2026-07-01

update

DA-Studio: An Agentic System for End-to-End Data Analysis

2026-07-01

update

Ask the World Before Acting: Budgeted Environment Probing for World-Model Calibration

2026-07-01

update

CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes

2026-07-01

update

UniTac: A Unified Multimodal Model for Cross-Sensor Tactile Understanding and Generation

2026-07-01

update

Zero-Shot Quantization for Object Detectors using Off-the-Shelf Generative Models

2026-07-01

update

CSTrader: A Testbed for Language-Grounded Trading in a Community-Driven Virtual Asset Market

2026-07-01

update

Team MKC at CLPsych 2026: Capturing and Characterizing Mental Health Changes through Social Media Timeline Dynamics

2026-07-01

update

Von Mises Based Uncertainty Quantification for Closely Spaced Automotive Radar Targets

2026-07-01

update

Surprise as a Signal for Plasticity and Metacognition

2026-07-01

update

Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models

2026-07-01

update

Design and Implementation of Agentic Orchestrations and Orchestration of Agents

2026-07-01

update

RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM Inference

2026-07-01

update

On the Convergence of Self-Improving Online LLM Alignment

2026-07-01

update

Beyond the Expressivity-Trainability Paradox: A Dynamical Lie Algebra Perspective on Navigating Barren Plateaus in Quantum Machine Learning

2026-07-01

update

ACE: Pluggable Adaptive Context Elasticizer across Agents

2026-07-01

update

Mitigating Positional Leakage in 3D Masked Autoencoders for Robust Representation Learning

2026-07-01

update

DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers

2026-07-01

update

Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning

2026-07-01

update

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models

2026-07-01

update

A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems

2026-07-01

update

FARS: A Fully Automated Research System Deployed at Scale

2026-06-30

update

Extrapolating from Regularised Solutions for Solving Ill-Conditioned Linear Systems in Machine Learning

2026-06-30

update

BayesEvolve: Explicit Belief States for Autonomous Scientific Discovery

2026-06-30

update

FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks

2026-06-30

update

REAR: Test-time Preference Realignment through Reward Decomposition

2026-06-30

update

Early Cue Precision Shapes Visual Shortcut Learning in Controlled Cue-Manipulation Benchmarks

2026-06-30

update

Residual-Guided Expert Specialization for Incomplete Multimodal Learning

2026-06-30

update

OLIVE: View-Augmented Latent Prediction with Waveform Reconstruction for Speech SSL

2026-06-30

update

On the Vulnerability of Parameter-Level Defenses to Model Merging

2026-06-30

update

Using Large Language Models as Low-Cost Statistical Estimators for Human-Response Data

2026-06-30

update

Set-Inclusive Uncertainty Modeling for Robust Brain Tumor Segmentation

2026-06-30

update

Scalar Representations of Neural Network Training Dynamics

2026-06-30

update

Predict, Reuse, and Repair: Accelerating Dynamic Sparse Attention for Long-Context LLM Decoding

2026-06-30

update

Beyond IID: How General Are Tabular Foundation Models, Really?

2026-06-30

update

Can LLMs Rank? A Tale of Triads and Triage

2026-06-30

update

Beyond Point Estimates for Glaucoma Visual Field Forecasting with Diffusion Models

2026-06-30

update

Translating Natural Language to Strategic Temporal Specifications via LLMs

2026-06-30

update

The FIL Hypothesis: Inductive Biases Help with Kernel Engineering

2026-06-30

update

On the Faithfulness of Post-Hoc Concept Bottleneck Models

2026-06-30

update

Discovering Collaboration from Novelty: Random Network Distillation for Clustered Federated Learning

2026-06-30

update

$μ$Flow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors

2026-06-30

update

Entity Binding Failures in Tool-Augmented Agents

2026-06-30

update

Linguistic Firewall: Geometry as Defense in Multi-Agent Systems Routing

2026-06-30

update

Poller: Are LLMs Suitable for Evaluating the Poetry Understanding Task?

2026-06-30

update

Convergence of Continual Learning in Homogeneous Deep Networks

2026-06-30

update

The Human Creativity Benchmark

2026-06-30

update

A Multi-task Mixture of Experts Framework for Malware Classification, Packing Detection, and Family Attribution

2026-06-30

update

SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions

2026-06-30

update

The Fundamental Limits of Valid Transport Map Estimation

2026-06-30

update

Beyond 2D Matching: A Unified Single-Stage Framework for Geometry-Aware Cross-View Object Geo-Localization

2026-06-30

update

Uncertainty-Aware Generation and Decision-Making Under Ambiguity

2026-06-30

update

Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection

2026-06-30

update

Wireless Backdoor Attack and Defense for Semantic Communications over Multiple Access Channel

2026-06-30

update

Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms

2026-06-30

update

DOPD: Dual On-policy Distillation

2026-06-30

update

GROW$^2$: Grounding Which and Where for Robot Tool Use

2026-06-30

update

VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes

2026-06-30

update

Exploiting Local Flatness for Efficient Out-of-Distribution Detection

2026-06-30

update

SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows

2026-06-30

update

SWE-Together: Evaluating Coding Agents in Interactive User Sessions

2026-06-30

update

DuoMem: Towards Capable On-Device Memory Agents via Dual-Space Distillation

2026-06-30

update

RiverONE: Generating Knowledge-Intensive VLM by Simulated Quantum Machines

2026-06-30

update

NeuReasoner: Theory-grounded Mapping of Reasoning Elicitation Boundaries

2026-06-30

update

First-Order Temporal Logic Tensor Networks

2026-06-30

update

Exploration and Online Transfer with Behavioral Foundation Models

2026-06-30

update

Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping

2026-06-30

update

AlgoSkill: Learning to Design Algorithms by Scheduling Human-Like Skills

2026-06-30

update

T3R: Deeper Test-Time Adaptation for Graph Neural Networks via Gradient Rotation

2026-06-30

update

Consensus Clustering of Free-Viewing Gaze Data: New Insights into Human-Information Interaction

2026-06-30

update

Heads, Not Backbones: Output Heads Dominate Architectures on Fat-Tailed Returns

2026-06-30

update

Building Multi-Task Agentic LLMs via Two-Phase Distillation

2026-06-30

update

Bridging the Gap Between Image Restoration and Navigational Safety in Hazy Conditions: A New Visibility Estimation Metric for Maritime Surveillance

2026-06-30

update

Data-Driven Energy-Based Learning via Gibbs Measures on Hierarchical Structures

2026-06-30

update

Neural Subspace Reallocation: Continual Learning as Retrieval-Based Subspace Memory Management

2026-06-30

update

ACPO: Agent-Chained Policy Optimization for Multi-Agent Reinforcement Learning

2026-06-30

update

Hierarchical Reinforcement Learning in StarCraft Micromanagement with Influence Maps and Cluster-based Scripts

2026-06-30

update

Efficient Retrieval-Augmented Generation via Token Co-occurrence Graphs

2026-06-30

update

Temporal Feature Extractors in EEG Foundation Models: A Controlled Comparison Including a Pretrained Time-Series Model

2026-06-30

update

Automating the Design of Embodied AgentArchitectures

2026-06-30

update

SA-VLA: State-aware tokenizer for improving Vision-Language-Action Models' performance

2026-06-30

update

Gravitational Duals from Equations of State II: Large Hierarchies and False Vacua

2026-06-30

update

Does Verbose Chain-of-Thought Really Help? In-Distribution Evidence that Content, Not Length, Matters

2026-06-30

update

Hyper-Network Neural Functional Maps for Unsupervised Robust 3D Shape Matching

2026-06-30

update

DNA Language Models: An Assessment of Pre-Training for Fine-Tuning Tasks

2026-06-30

update

Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark

2026-06-30

update

Dynamo: Dynamic Skill-Tool Evolution for Vision-Language Agents

2026-06-30

update

DAIN: Dynamic Agent-Based Interaction Network for Efficient and Collaborative Multimodal Reasoning

2026-06-30

update

From Detecting Agency to Doing Work: Self-Caused Credit Builds a Durable Behavioral Self in a Minimal Spiking Agent

2026-06-30

update

Domain Adaptation with Adaptive Imagination for Visual Reinforcement Learning under Limited Target Data

2026-06-30

update

Efficient RGB-T Object Detection via Sparse Cross-Modality Fusion

2026-06-30

update

Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning

2026-06-30

update

B3O: Scalable Boltzmann Batch Bayesian Optimization

2026-06-30

update

A Distributionally Robust Framework for Learned Reconstructions in Inverse Problems

2026-06-30

update

CaresAI at CT-DEB26: Detecting Dosing Errors In Clinical Trials Using Domain-Specific Transformer Embeddings and Classification Models

2026-06-30

update

Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration

2026-06-30

update

Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation

2026-06-30

update

Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors

2026-06-30

update

KnowsTFM: Knowledge-Informed Fine-Tuning of Small Tabular Foundation Models

2026-06-30

update

Defending Against Harmful Supervision Hidden in Benign Samples

2026-06-30

update

Towards Continual Motion-Language Agents: LoRA Variants for Incremental Motion Understanding and Generation

2026-06-30

update

PromptGNN-sim: Deep Fusion and Alignment of GNN and LLMs for Text-Attributed Graph Learning

2026-06-30

update

ManimAgent: Self-Evolving Multimodal Agents for Visual Education

2026-06-30

update

Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents

2026-06-30

update

BrainJanus: A Unified Model for Understanding and Generation across Brain, Vision, and Language

2026-06-30

update

Forward-Future/loopy：A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows.

2026-06-29

update

Applicability of memorization indicators for early spotting of overfitting while recalibrating sEMG-decoders on low sample sizes

2026-06-29

update

S$^2$-VLA: State-Space Guided Vision-Language-Action Models for Long-Horizon Manipulation

2026-06-29

update

SpatialUAV: Benchmarking Spatial Intelligence for Low-Altitude UAV Perception, Collaboration, and Motion

2026-06-29

update

A Study of Temporal Fusion Strategies for Named Entity Recognition in Historical Texts

2026-06-29

update

Mosaic: A Benchmark Suite for Differentiable Physics Solvers

2026-06-29

update

Home3D 1.0: A High-Fidelity Image-to-3D Asset Generation System for Interior Design

2026-06-29

update

Agentic AI-Powered Re-Identification: An Emerging, Scalable Threat to Mobility Microdata Privacy

2026-06-29

update

AI Persuasive Framing in Collective Dilemmas

2026-06-29

update

An Empirical Analysis of Factual Errors in Human-Written Text and its Application

2026-06-29

update

Reasoning Beyond Prediction: From Data-Driven to Causal Software Engineering

2026-06-29

update

ToxiREX: A Dataset on Toxic REasoning in ConteXt

2026-06-29

update

Benchmarking on Tasks That Matter: Dataset Selection for Preserving Model Rankings

2026-06-29

update

Dialogue to Detection: A Multimodal Hybrid NLP Pipeline for Insurance Fraud Detection

2026-06-29

update

Can LLMs Judge Better Than They Generate? Evaluating Task Asymmetry, Mechanistic Interpretability and Transferability for In-Context QA

2026-06-29

update

ToolPrivacyBench: Benchmarking Purpose-Bound Privacy in Tool-Using LLM Agents

2026-06-29

update

Single and Multi Truth Data Fusion using Large Language Models

2026-06-29

update

JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications

2026-06-29

update

OSOR: One-Step Diffusion Inpainting for Effect-Aware Object Removal

2026-06-29

update

Cross-view Multimodal Vision-Based Assessment Framework for Traditional Chinese Medicine Rehabilitation Training

2026-06-29

update

When One Adapter Speaks for Many: Discovering Low-Rank Redundancy in Continual Fine-Tuning

2026-06-29

update

Beyond Sparse Supervision: Diffusion-Guided Learning for Few-Shot Graph Fraud Detection

2026-06-29

update

Toward Robust In-Context Segmentation via Concept Guidance

2026-06-29

update

Regularized Reward-Punishment Reinforcement Learning

2026-06-29

update

EchoSonar-R: A Multi-View Reasoning-Enabled Model for Disease Classification and Report Generation in Echocardiography

2026-06-29

update

CPAgents: Agentic Composite Phenotype Generation for Cardiac Disease Association

2026-06-29

update

LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior

2026-06-29

update

The Remittance Blueprint: Data-driven Intelligence for Sri Lanka

2026-06-29

update

COCOLogic-V2: Identifying Logical Inconsistencies via Truly Hard-Negatives

2026-06-29

update

Govern the Repository, Not the Agent: Measuring Ecosystem-Level Risk in AI-Native Software

2026-06-29

update

Bridging Ab Initio Symmetries and Global Nuclear Masses with Interpretable Neural Networks

2026-06-29

update

Democratic ICAI: Debating Our Way to Steering Principles from Preferences

2026-06-29

update

VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing

2026-06-29

update

Which Nash Equilibrium? Solver-Dependent Selection on Zero-Sum Nash Polytopes

2026-06-29

update

DexCompose: Reusing Dexterous Policies for Multi-Task Manipulation with a Single Hand

2026-06-29

update

AI boom risks global financial crash, warn central bankers

2026-06-27

update

Task Failed Successfully: Saturating NIC and Disk Bandwidth

2026-06-27

update

Aircraft crashes into Beijing's tallest skyscraper, triggering evacuations

2026-06-26

update

Einstein World Models

2026-06-26

update

XMSE-Aware Adaptive Empirical Bayes Estimation

2026-06-26

update

In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics

2026-06-26

update

Decision-Aligned Evaluation of Uncertainty Quantification

2026-06-26

update

Event-Aware Instructed Assistant for Referring Video Segmentation

2026-06-26

update

On-board Remote-Sensing Foundation Models for Unsupervised Change Detection of Disaster Events

2026-06-26

update

ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP

2026-06-26

update

Symplectic Neural Networks for learning Generalized Hamiltonians

2026-06-26

update

The Spec Growth Engine: Spec-Anchored, Code-Coupled, Drift-Enforced Architecture for AI-Assisted Software Development

2026-06-26

update

NuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language Models

2026-06-26

update

Towards Explainable Adjudicative Variance: Quantifying Judicial Discretion via Gated Multi-Task Learning

2026-06-26

update

Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation

2026-06-26

update

Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning

2026-06-26

update

The Riddle Riddle: Testing Flexible Reasoning in Large Language Models and Humans

2026-06-26

update

Application of LLMs to Threat Assessment of Foreign Peacekeeping Missions

2026-06-26

update

Cross-Head Attention Uplift Network with Inverse Propensity Score under Unobserved Confounding

2026-06-26

update

Efficient foundation decoders for fault-tolerant quantum computing

2026-06-26

update

Kolmogorov Arnold networks (KAN) for aerodynamic prediction: a comparison with MLPs and GNNs

2026-06-26

update

Joint Learning of Experiential Rules and Policies for Large Language Model Agents

2026-06-26

update

Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks

2026-06-26

update

OpenRCA 2.0: From Outcome Labels to Causal Process Supervision

2026-06-26

update

TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference

2026-06-26

update

Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)

2026-06-26

update

RecallRisk-BERT: A Multi-Task Framework for Post-Report Medical Device Recall Triage

2026-06-26

update

Automating Potential-based Reward Shaping with Vision Language Model Guidance

2026-06-26

update

HarmVideoBench: Benchmarking Harmful Video Understanding in Large Multimodal Models

2026-06-26

update

A Process Harness for Uplifting Legacy Workflows to Agentic BPM: Design and Realization in CUGA FLO

2026-06-26

update

Forecasting With LLMs: Improved Generalization Through Feature Steering

2026-06-26

update

Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement

2026-06-26

update

Bridging Talk and Thought: Understanding Dialogue Dynamics Across Collaborative Problem-Solving Contexts

2026-06-26

update

LMs as Task-Specific Knowledge Bases: An Interpretability Analysis

2026-06-26

update

The Geometry of Updates: Fisher Alignment at Vocabulary Scale

2026-06-26

update

E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation

2026-06-26

update

BetXplain: An Explanation-Annotated Dataset for Detecting Manipulative Betting Advertisements on Social Media

2026-06-26

update

How Surprising Is Historical Italian to Language Models? Tokenization Tax, Comprehension Tax, and a Simple Mitigation

2026-06-26

update

EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting

2026-06-26

update

Recovering Governing Equations from Solution Data: Identifiability Bounds for Linear and Nonlinear ODEs

2026-06-26

update

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models

2026-06-26

update

Designing Reward Signals for Portable Query Generation: A Case Study in Industrial Semantic Job Search

2026-06-26

update

Multilingual Reasoning Cascades Need More Context

2026-06-26

update

Beyond Surface Forms: A Comprehensive, Mechanism-Oriented Taxonomy of Indirect Linguistic Encoding for LLM-Based Coded Language Detection

2026-06-26

update

LLM-Based Examination of Eligibility Criteria from Securities Prospectuses at the German Central Bank

2026-06-26

update

Hallucination in World Models is Predictable and Preventable

2026-06-26

update

Mapping Political-Elite Networks in Europe with a Multilingual Joint Entity-Relation Extraction Pipeline

2026-06-26

update

Error-Conditioned Neural Solvers

2026-06-26

update

Apple to skip high-end M6 Mac chips in favor of AI-focused M7 line

2026-06-26

update

google-deepmind/science-skills：GDM Science Skills to speed up agentic scientific workflows with better grounding and higher token efficiency. Integrate insights from AlphaGenome, AFDB, UniProt and 30+ other databases and tools.

2026-06-25

update

Statistically Valid Hyperparameter Selection: From Tuning to Guarantees

2026-06-25

update

Constraint Tax in Open-Weight LLMs: An Empirical Study of Tool Calling Suppression Under Structured Output Constraints

2026-06-25

update

Probabilistic Agents in Deterministic Audits: Evaluating Multi-Agent Systems for Automated Audits Based on the German IT-Grundschutz

2026-06-25

update

Taxonomy of Risks on Automated Fact-Checking Systems Considering its Propagation

2026-06-25

update

MedGuards: Multi-Agent System for Reliable Medical Error Detection and Correction

2026-06-25

update

Power-Budgeted Underwater Vehicle Control via Constrained Reinforcement Learning

2026-06-25

update

Memory-Efficient Policy Libraries with Low-Rank Adaptation in Reinforcement Learning

2026-06-25

update

GUI agent: Guided Exploration of User-Sensitive Screens

2026-06-25

update

Cellular Predictions on the Move: What about Data?

2026-06-25

update

Point Cloud Diffusion with Global and Local Reconstruction for Instance-Level 3D Anomaly Detection

2026-06-25

update

Gaussian Mean Field Variational Inference can Overestimate Predictive Variance

2026-06-25

update

Gradient-based inverse lithography for EUV masks via the waveguide method and a physics-informed neural operator

2026-06-25

update

Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasets

2026-06-25

update

Bridging Spherical Black-Box Optimizers

2026-06-25

update

Re-mixing Embeddings for Patient Augmentation in Data Scarce Multiple Instance Learning

2026-06-25

update

Hierarchical Graph Learning for Calendar Spread Strategies in Commodity Futures Markets

2026-06-25

update

Beyond Function Calling: Benchmarking Tool-Using Agents under Tool-Environment Unreliability

2026-06-25

update

MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources

2026-06-25

update

AI Snitches Get Glitches: Towards Evading Agentic Surveillance

2026-06-25

update

Edges Before Embeddings: A Confidence-Aware Blur Gate for Vision-Language Pipelines

2026-06-25

update

Semantic Consistency Policy Optimization for Reinforcement Learning of LLM Agents

2026-06-25

update

Color Matters: Trigger Color Affects Success in Federated Backdoor Attacks

2026-06-25

update

AutoRelAnnotator: Calibrated Model Cascades for Cost-Efficient Relevance Evaluation in Sponsored Search

2026-06-25

update

Overview of HIPE-2026: Person-Place Relation Extraction from Multilingual Historical Texts

2026-06-25

update

Pulmonary Embolism Risk Stratification from CTPA and Medical Records: Vascular Graphs Are Not All You Need

2026-06-25

update

SE-AGCNet: An End-to-End Framework for Joint Speech Enhancement and Loudness Control in Meeting Scenarios

2026-06-25

update

Agentic System as Compressor: Quantifying System Intelligence in Bits

2026-06-25

update

Helpful or Harmful? Evaluating LLM-Assisted Vulnerability Patching via a Human Study

2026-06-25

update

Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound

2026-06-25

update

Weave of Formal Thought

2026-06-25

update

Taxonomy-aware deep learning for hierarchical marine species classification in underwater imagery

2026-06-25

update

Autodata: An agentic data scientist to create high quality synthetic data

2026-06-25

update

Dziri Voicebot: An End-to-End Low-Resource Speech-to-Speech Conversational System for Algerian Dialect

2026-06-25

update

FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation

2026-06-25

update

Privacy Vulnerabilities of Attention Layers in Tabular Foundation Models and Protection of High-Risk Queries

2026-06-25

update

Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It

2026-06-25

update

TriViewBench: Controlled Complexity Scaling for Multi-View Structural Reasoning in MLLMs

2026-06-25

update

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning

2026-06-25

update

AI translation of literary texts is "fine", but readers still prefer human translations

2026-06-25

update

How Robust is OCR-Reasoning? Evaluating OCR-Reasoning Robustness of Vision-Language Models under Visual Perturbations

2026-06-25

update

A welding penetration prediction model for laser welding process based on self-supervised learning using physics-informed neural networks

2026-06-25

update

A cross-process welding penetration status prediction algorithm based on unsupervised domain adaptation in laser and TIG welding

2026-06-25

update

Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents

2026-06-25

update

On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity

2026-06-25

update

Learning Action Priors for Cross-embodiment Robot Manipulation

2026-06-24

update

Measuring User's Mental Models of Speech Translation in Human-AI Collaboration

2026-06-24

update

A Physics-Informed Fourier-Wavelet Transformer for Multiscale Computational Fluid Dynamics Surrogate Modeling

2026-06-24

update

Model selection with proper scoring rules on data sets of time series

2026-06-24

update

Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations

2026-06-24

update

Task Decomposition for Efficient Annotation

2026-06-24

update

Beyond U-Net: A Latent-Representation-Aligned Skip-Free Backbone for Flow-Matching Speech Enhancement

2026-06-24

update

Scaling Laws for Task-Specific LLM Distillation

2026-06-24

update

Can Scale Save Us From Plasticity Loss in Large Language Models?

2026-06-24

update

CANDLE: Character-level Arabic Noise Deduplication using Lightweight Encoder

2026-06-24

update

UniDrive: A Unified Vision-Language and Grounding Framework for Interpretable Risk Understanding in Autonomous Driving

2026-06-24

update

Posterior Refinement: Fast Language Generation via Any-Order Flow Maps

2026-06-24

update

Are We Ready For An Agent-Native Memory System?

2026-06-24

update

Paying to Know: Micro-Transaction Markets for Verified Product Information in Agentic E-Commerce

2026-06-24

update

Grad Detect: Gradient-Based Hallucination Detection in LLMs

2026-06-24

update

EG-VQA: Benchmarking Verifiable Video Question Answering with Grounded Temporal Evidence

2026-06-24

update

OrbitForge: Text-to-3D Scene Generation via Reconstruction-Anchored Video Synthesis

2026-06-24

update

SHERLOC: Structured Diagnostic Localization for Code Repair Agents

2026-06-24

update

L3Cube-MahaPOS: A Marathi Part-of-Speech Tagging Dataset and BERT Models

2026-06-24

update

Grading the Grader: Lessons from Evaluating an Agentic Data Analysis System

2026-06-24

update

Matching Tasks to Objectives: Fine-Tuning and Prompt-Tuning Strategies for Encoder-Decoder Pre-trained Language Models

2026-06-24

update

IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation

2026-06-24

update

InSight: Self-Guided Skill Acquisition via Steerable VLAs

2026-06-24

update

SP-Mind: An Autonomous Reasoning Agent for Spatial Proteomics Analysis

2026-06-24

update

Automated Residual Plot Assessment With the R Package autovi and the Shiny Application autovi.web

2026-06-24

update

Social Structure Matters in 3D Human-Human Interaction Generation

2026-06-24

update

SURGELLM: Rethinking Multi-Task Evaluation through Task-Aware Feature Gating with Class-Balanced Normalization

2026-06-24

update

MotifGen: Spatiotemporal interpolation of misaligned satellite images via multi-source generative modeling, in an application to tropical cyclones

2026-06-24

update

Pigeonholing: Bad prompts hurt models to collapse and make mistakes

2026-06-24

update

CALIBER: Calibrating Confidence Before and After Reasoning in Language Models

2026-06-24

update

Prob-BBDM: a Probabilistic Brownian Bridge Diffusion Model for MRI sequence image-to-image translation

2026-06-24

update

Managing Task Execution for Unknown Workloads in Batteryless IoT: A Hardware-Agnostic Evaluation

2026-06-24

update

PETRA: Transforming Web Text for Petroleum-Engineering Domain Adaptation

2026-06-24

update

Automatic Part-of-Speech Tagging of Arabic-English Dictionary Senses through WordNet

2026-06-24

update

On the Stability of Prompt Ranking in Large Language Model Evaluation

2026-06-24

update

ATRIA: Adaptive Traceable ECG Reporting with Iterative Agents

2026-06-24

update

Average Rankings Mask Per-Subject Optimality: A Friedman-Nemenyi Benchmark of EEG Motor-Imagery BCI Decoders

2026-06-24

update

RE4: Transformation-aware Imitation of Object Interactions Using Manipulation Modes

2026-06-24

update

Beyond Logprobs: A Multi-Signal Confidence Engine for LLM-Based Document Field Extraction

2026-06-24

update

Can Aggregate Invariants Accelerate Continuous Subgraph Matching? Limits, Laws, and a Dynamic Spectral Index

2026-06-24

update

Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning

2026-06-24

update

Transformation Behavior of Images in Latent Space

2026-06-24

update

MedPCFM: Improving Medical Point Cloud Completion by Integrating Point Transformers and Flow Matching

2026-06-24

update

NoContactNoWorries: Estimating Contact through Vision and Proprioception for In-Hand Dexterous Manipulation

2026-06-24

update

G$^3$VLA: Geometric inductive bias for Vision-Language-Action Models

2026-06-24

update

video-SALMONN-R$^3$: Learning to ReWatch, ReAsk, and ReAnswer for Efficient Video Understanding

2026-06-24

update

UOL@IDEM at BEA 2026 Shared Task 1: Neural Fusion and Feature-Rich Modeling for L1-Aware Vocabulary Difficulty Prediction

2026-06-24

update

A Fair Evaluation of Graph Foundation Models for Node Property Prediction

2026-06-24

update

Reinforcement Learning for Computer-Use Agents with Autonomous Evaluation

2026-06-24

update

AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning

2026-06-24

update

NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?

2026-06-24

update

Quant Convergence: Bridging Classical Value Investing and Modern Factor Models for Systematic Equity Selection

2026-06-24

update

EERLoss: A Novel Loss Function for Training Deep Biometric Models. A Case Study in Keystroke Dynamics

2026-06-24

update

MEMPROBE: Probing Long-Term Agent Memory via Hidden User-State Recovery

2026-06-24

update

To Compare, or Not to Compare: On Methodological Practices in Evaluating Social Bias

2026-06-24

update

When CQs Go Wrong: Challenges in CQ Verification with OE-Assist

2026-06-24

update

Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity

2026-06-24

update

SAFARI: Scaling Long Horizon Agentic Fault Attribution via Active Investigation

2026-06-24

update

CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning

2026-06-24

update

Show HN: Y – A malleable coding-agent desktop app built with Electron

2026-06-23

update

Abstract representational geometry supports inference in large language models

2026-06-23

update

Adaptive Hard-Soft Physics-Informed Neural Networks for Robust Boundary-Constrained PDE Solving

2026-06-23

update

Measuring & Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts

2026-06-23

update

Distribution-Aware Diffusion-LLM for Robust Ultra-Long-Term Time Series Forecasting

2026-06-23

update

Litmus: Zero-Label, Code-Driven Metric Specification for Evaluating AI Systems

2026-06-23

update

Detecting Malicious Agent Skills in the Wild using Attention

2026-06-23

update

Rethinking Object-Centric Representations for Video Dynamics Modeling

2026-06-23

update

SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors

2026-06-23

update

Selective Time Series Forecasting via Metalearning

2026-06-23

update

AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure Interaction

2026-06-23

update

Time Series Classification through Diffeomorphic Time Warping (DiffTW)

2026-06-23

update

Sublinearly Structured Deep Neural Networks Achieve Feature Learning Consistency for Compositional Functions

2026-06-23

update

Concordia: JIT-Compiled Persistent-Kernel Checkpointing for Fault-Tolerant LLM Inference

2026-06-23

update

Self-Compacting Language Model Agents

2026-06-23

update

SQLConductor: Search-to-Policy Learning for Step-wise Text-to-SQL Orchestration

2026-06-23

update

Approximating velocity fields with planted attractors via Neural-ODEs for classification purposes

2026-06-23

update

LangMAP: A Language-Adaptive Approach to Tokenization

2026-06-23

update

Scheduling Thoughts: Learning the Order of Thought in Diffusion Language Models

2026-06-23

update

Solve for the Hyperparameter, Skip the Search: Kolmogorov-Optimal Scaling Laws for Spline Regression

2026-06-23

update

Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse

2026-06-23

update

Evaluation Awareness Is Not One Capability: Evidence from Open Language Models

2026-06-23

update

It's Much Easier for Neural Networks to learn Game of Life Dynamics with the Right Activation Function: Polynomial Kolmogorov-Arnold Networks

2026-06-23

update

A Generative Model for Closed-Loop Microsimulation of Signalized Intersections

2026-06-23

update

SPIRAL: Learning to Search and Aggregate

2026-06-23

update

Polycepta: Object-Centric Appearance Estimation for Multi-Object Tracking

2026-06-23

update

Causal Discovery in the Era of Agents

2026-06-23

update

Hedgementation = Hedgerow Segmentation: A Remote Sensing Benchmark

2026-06-23

update

RECALL: Recovery Experience Collection for Active Lifelong Learning in Vision-Language-Action Models

2026-06-23

update

DiT-Reward: Generative Representations for Text-to-Image Reward Modeling

2026-06-23

update

Learning Process Rewards via Success Visitation Matching for Efficient RL

2026-06-23

update

EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions

2026-06-23

update

Action-BED: Task-Driven Bayesian Experimental Design with Singly Intractable Objectives

2026-06-23

update

MAS-PromptBench: When Does Prompt Optimization Improve Multi-Agent LLM Systems?

2026-06-23

update

On the Limits of Prompt-Conditioned Language Models as General-Purpose Learners

2026-06-23

update

Can LLMs Reliably Self-Report Adversarial Prefills, and How?

2026-06-23

update

Teaching LLMs String Matching, Backtracking, and Error Recovery to Deduce Bases and Truth Tables for the Combinatorially Exploding Bit Manipulation Puzzles

2026-06-23

update

PsyBridge: A Hybrid Intelligent Framework for Multi-Dimensional Mental Health Assessment and Decision Support

2026-06-23

update

Semantic Browsing: Controllable Diversity for Image Generation

2026-06-23

update

CoorDex: Coordinating Body and Hand Priors for Continuous Dexterous Humanoid Loco-Manipulation

2026-06-23

update

Revelio: Cost-Efficient Agentic Memory Safety Vulnerability Detection For Repository-Scale Codebases

2026-06-23

update

MixedPEFT: Combining Multiple PEFT Methods with Mixed Objectives for Unsupervised Domain Adaptation

2026-06-23

update

Any-Body Guard: Universal Safeguarding for Manipulation Policies via Action Masking

2026-06-23

update

SCENIC: Semantic-Conditioned Edge-Aware Neural Framework for Structured IoT Command Generation

2026-06-23

update

Encoder-Decoder Manifold Alignment for Idempotent Generation

2026-06-23

update

Enhancing Protein Representation Learning via Manifold Restore Mixing

2026-06-23

update

Specificity- and Calibration-Aware Breast Ultrasound Segmentation via Entropy-Guided Boundary Supervision

2026-06-23

update

Benchmarking Robot Memory Under Interference

2026-06-23

update

A Taxonomy of Conceptual Alignment in Human-Robot Dialogue

2026-06-23

update

Reference-Free Assessment of Physical Consistency in World Model-based Video Generation

2026-06-23

update

ARIA: A Causal-Aware Framework for Rescuing LLM Reasoning in Trustworthy Materials Discovery

2026-06-23

update

Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers

2026-06-23

update

MetaPS: Adaptive Programmatic Strategy Selection for Market Agents

2026-06-23

update

PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems

2026-06-23

update

Multi-cancer detection using a computationally efficient CNN with transfer learning

2026-06-23

update

Knowledge-Graph Grounding Helps LLMs Only for Out-of-Training Knowledge: A Controlled Study on Clinical Question Answering

2026-06-23

update

QeHDC: Hyperdimensional Computing based on Quantum-enhanced binding and SuperClass Construction

2026-06-23

update

Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation

2026-06-23

update

Escaping the Variance Trap: Jacobian-Free Dynamics for Root-Finding Bilevel Optimization

2026-06-23

update

Distribution-Aware Robust Bilevel Optimization: Quantile-Guided Huber Updates in Two-Timescale Stochastic Approximation

2026-06-23

update

Efficient Multimodal Clinical Question Answering for Pulmonary Embolism Risk Assessment

2026-06-23

update

Adaptive Recurrent Message Passing for Test Time Computing on Graphs

2026-06-23

update

Not All Claims Are Equally Risky: FACTOR for Adaptive Verification in Factual Long-Form Generation

2026-06-23

update

VADAOrchestra: Neurosymbolic Orchestration of Adaptive Reasoning Workflows

2026-06-23

update

Human and AI collaboration for pulmonary nodule segmentation

2026-06-23

update

SCOPE: Evolving Symbolic World for Planning in Open-Ended Environments

2026-06-23

update

Grounded Scaling: Why Agentic AI Needs Deterministic Environments

2026-06-23

update

Imagine to Ensure Safety in Hierarchical Reinforcement Learning

2026-06-23

update

Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do

2026-06-23

update

Deep material network for homogenization of piezoelectric composites

2026-06-23

update

Concept-Constrained Prompt Learning for Few-Shot CLIP Adaptation

2026-06-23

update

Text2DSL: LLM-Based Code Generation for Domain-Specific Languages

2026-06-23

update

Training-free Task Classification for Multi-Task Model Merging

2026-06-23

update

Automated sign detection across the Electronic Babylonian Library: A large-scale dataset and end-to-end cuneiform OCR pipeline

2026-06-23

update

PaperClaw: Harnessing Agents for Autonomous Research and Human-in-the-Loop Refinement

2026-06-23

update

Communication Heterogeneity and Collective Consensus in Neural Cellular Automata

2026-06-23

update

QBioFusion-QSAR: Morgan-Anchored Quantum Multiple Kernel Learning for Small-Data Ligand Classification

2026-06-23

update

ACE-GS: Acing the Trade-off with Accurate, Compact and Efficient 3D Gaussian Splatting

2026-06-23

update

Subsampling for supervised learning in reproducing kernel Hilbert spaces

2026-06-23

update

Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization

2026-06-23

update

Reconstructing Randomly Masked Spectra Helps DNNs Identify Discriminant Wavenumbers

2026-06-23

update

Topological Neural Dynamics: A Neuron-wise Framework for Sequence Modeling

2026-06-23

update

NASDAQ: Normalized Observation Space Dynamics-Augmented Q-Learning

2026-06-23

update

Task-Differentiated Atomic Skill Expansion and Routing for Continual Learning Across Highly Heterogeneous Tasks

2026-06-23

update

DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams

2026-06-23

update

An Evaluation Framework for Text-to-Speech Voice Reconstruction

2026-06-23

update

A Reward-Petri-Net Interpretation of Temporal Behavior Trees

2026-06-23

update

Urban Power Grid Topology and Hierarchy Identification from Open Data

2026-06-23

update

SOHET: Sequence Of Heterogeneous Events Transformer with Self-Supervised Pre-Training

2026-06-23

update

Finetuning with Scientific Data Increases Hallucinations: A Multi-domain Factuality Evaluation of LLMs

2026-06-23

update

NAC: Neural Action Codec for Vision-Language-Action Models

2026-06-23

update

Enhancing Creativity in 3D Generative Design via a TRIZ-Inspired Text-to-CAD Framework

2026-06-23

update

VLA-FAIL: Efficient Task Failure Detection for Finetuned Vision-Language-Action Models

2026-06-23

update

2D Versus 3D Diffusion for In Silico Training of Interventional X-ray AI Models

2026-06-23

update

Dual-Attention Convolution Experts for Sparse Tensor Completion

2026-06-23

update

Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study

2026-06-23

update

AutoRAS: Learning Robust Agentic Systems with Primitive Representations

2026-06-23

update

ASCII Art Turns LLMs into VLA Controllers

2026-06-23

update

Robustness Cannot be Reduced to Regularization: Studying Adversarial Training Beyond the Linear Case

2026-06-23

update

Predicting High-Risk Colorectal Polyps in African Americans Using Pre-Colonoscopy Clinical Features: Machine Learning Model Development and Temporal Validation

2026-06-23

update

Decoupling the Declarative from the Procedural in Vision-Language-Action Models

2026-06-23

update

Breaking chains with trees: Deep learning with $\mathcal{O}(\log N)$ parallel time complexity

2026-06-23

update

Towards Understanding the Power and Limits of the Muon Optimizer: A River-Valley Perspective

2026-06-23

update

Backpropagating Through Simulation: Analytic Policy Gradients for Sample and Learning Efficient Differentiable Continuous Control

2026-06-23

update

PeerMathDial: A Middle School Dialogue Dataset for Student Collaborative Math Problem Solving

2026-06-23

update

The Unreasonable Effectiveness of VLMs for Zero-shot Procedural Mistake Detection

2026-06-23

update

FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous Driving

2026-06-23

update

Blogger Defeats Photographer's Copyright Claim-Sokolskyfilm vs. Messiah

2026-06-22

update

You're probably using Agent Skills wrong

2026-06-22

update

ningzimu/codex-ppt-skill：GPT-Image-2 PPT Generator Skill for Creating Image-Based PowerPoint Presentations in Codex and Other Skill-Compatible Agents

2026-06-21

update

BuilderIO/skills：Skills for coding agents

2026-06-21

update

muxuuu/serenity-skill：Serenity-inspired Agent Skill for supply-chain bottleneck stock research

2026-06-21

update

0x0funky/agent-sprite-forge：Agent Skill for generating 2D sprite sheets and map, transparent PNG frames, and animated GIFs from prompts.

2026-06-21

update

anysearch-ai/anysearch-skill：Unified real-time search engine skill for AI agents.

2026-06-21

update

OpenBMB/PilotDeck：Task-oriented AI Agent productivity platform

2026-06-21

update

earthtojake/text-to-cad：A collection of agent skills for CAD, robotics and hardware design

2026-06-21

update

microsoft/SkillOpt：SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

2026-06-21

update

op7418/guizang-ppt-skill：AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.

2026-06-21

update

Slow breathing modulates brain function and risk behavior

2026-06-20

update

Introducing LifeSciBench

2026-06-20

update

Evaluating and Enhancing Negation Comprehension in Remote Sensing MLLMs

2026-06-20

update

Effective Dimension Governs Generalization in Quantum Kernel Vision Models

2026-06-20

update

HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-trainin

2026-06-20

update

Pitch Spelling Jazz Lead Sheets, Solo Transcriptions, Classical Piano and Monophonic Scores

2026-06-20

update

Apparent Psychological Profiles of Large Language Models are Largely a Measurement Artifact

2026-06-20

update

FlowMaps: Modeling Long-Term Multimodal Object Dynamics with Flow Matching

2026-06-20

update

CzechDocs: A Multiway Parallel Dataset of Formatted Documents for Minority Languages in Czechia

2026-06-20

update

QMFOL: Benchmarking Large Language Model Reasoning via Quantifiable Monadic First-Order Logic Test Case Generation

2026-06-20

update

A Multi-Agent system for Multi-Objective constrained optimization

2026-06-20

update

SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs

2026-06-20

update

Navigating Unreliable Parametric and Contextual Knowledge: Explicit Knowledge Conflict Resolution for LLM Inference

2026-06-20

update

Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think

2026-06-20

update

The Register Gap: A Meaning Intelligence Framework for Nigerian Public Discourse

2026-06-20

update

Confidence-Aware Automated Assessment of Student-Drawn Scientific Models

2026-06-20

update

Lagrange: An Open-Vocabulary, Energy-Based Sparse Framework for Generalized End-to-End Driving

2026-06-20

update

ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval

2026-06-20

update

Statistical Properties of Training & Generalization

2026-06-20

update

Recurrent neural networks approximate continuous functions

2026-06-20

update

Robust $Q$-learning for mean-field control under Wasserstein uncertainty in common noise

2026-06-20

update

Automating SKILL.md Generation for Computer-Using Agents via Interaction Trajectory Mining

2026-06-20

update

AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning

2026-06-20

update

CRAX: Fast Safe Reinforcement Learning Benchmarking

2026-06-20

update

Towards Modality-imbalanced Federated Graph Learning: A Data Synthesis-based Approach

2026-06-20

update

Pseudo-Feature Padding: A Lightweight Defense Against False Data Injection in Power Grids

2026-06-20

update

Sparsity, Superposition, and Forgetting: A Mechanistic Study of Representation Retention in Continual Learning

2026-06-20

update

SSH-Net: A Deep Neural Network for Predicting Failure Time Distribution Functions under Competing Risks with Application to GPU Data

2026-06-20

update

Scalable Training of Spatially Grounded 2D Vision-Language Models for Radiology

2026-06-20

update

Optimal Order of Multi-Agent and General Many-Body Systems

2026-06-20

update

Beyond Global Replanning: Hierarchical Recovery for Cross-Device Agent Systems

2026-06-20

update

Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages

2026-06-20

update

LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents

2026-06-20

update

Multi-Task Bayesian In-Context Learning

2026-06-20

update

Toward Calibrated Mixture-of-Experts Under Distribution Shift

2026-06-20

update

Optimal Deterministic Multicalibration and Omniprediction

2026-06-20

update

UNIEGO: Proxies as Mediators for Unified Egocentric Video Representation Learning

2026-06-20

update

How Transparent is DiffusionGemma?

关联动态

图卷积注意力：从谱视角看图去噪与扩散

本文从谱图理论出发，重新审视图卷积中的注意力机制，讨论其如何在图结构上同时实现去噪与扩散。作者将注意力权重解释为对不同频率成分的自适应滤波，说明其不仅影响邻居信息的聚合方式，也决定了信号在图上的平滑、保留边界与抑制噪声的平衡。文章进一步把该视角与图扩散过程联系起来，分析注意力在传播范围、稳定性和过平滑问题中的作用。该研究为理解图神经网络的表达能力提供了更统一的理论框架，也为设计更稳健的图学习模型提供了启发。

来源 arXiv 时间 2026-07-07 17:52:17

通过视觉动作结果推理对齐连接物理推理与任务泛化

本文聚焦具身智能中的一个核心难题：模型往往能在训练场景中完成动作，却难以将对物理世界的理解迁移到新任务与新环境。作者提出一种“视觉动作结果推理对齐”思路，把对动作后果的视觉推断与物理推理能力进行显式对齐，使模型不仅判断“该怎么做”，还学习“做完会发生什么”。这种机制有助于把局部感知、动作选择与结果预测统一起来，从而提升对未见任务的泛化能力。研究强调，真正稳健的任务执行不只依赖表面模式匹配，而需要可迁移的物理因果理解。

来源 arXiv 时间 2026-07-07 17:27:59

FreqDepthKV：面向长上下文推理的频率引导深度共享KV缓存压缩

这篇工作聚焦大模型长上下文推理中的KV Cache膨胀问题，提出 FreqDepthKV，一种结合“频率信息”与“深度共享”的缓存压缩方法。其核心思路是：并非所有注意力头或层对上下文记忆同等重要，可以利用表示频率特征来判断哪些KV更值得保留，并通过跨层共享降低冗余存储。相比传统只按重要性裁剪或简单量化的做法，FreqDepthKV更强调在压缩率与推理稳定性之间取得平衡，目标是在尽量少损失生成质量的前提下显著降低显存占用，提升长文本推理的可扩展性。

来源 arXiv 时间 2026-07-07 17:26:28

Pitwall：基于校准实时蒙特卡洛引擎的赛道策略自然语言简报

本文提出 Pitwall，一套将实时蒙特卡洛仿真与自然语言生成结合的赛车策略简报系统。它面向比赛中的战术决策场景，先通过校准后的概率模型持续评估安全车、进站、胎况与名次变化等关键变量，再把数值结果转写为面向工程师和车队的自然语言建议。与只输出分数或概率的传统系统不同，Pitwall 强调“忠实表达”——生成内容必须严格对应仿真结果，避免夸大、遗漏或不一致。研究重点在于把实时推演、置信度校准和可读性三者统一起来，从而为高时效、高风险的赛车策略提供可解释、可执行的语言化支持。

来源 arXiv 时间 2026-07-07 16:55:39

AirflowAttack：面向红外遥感视觉语言模型的热气流对抗扰动攻击

本文提出 AirflowAttack，一种针对红外遥感视觉语言模型的物理对抗攻击方法。与传统像素级扰动不同，该方法利用热气流在红外成像中的传播与扰动效应，通过构造可在真实环境中产生影响的热-气流扰动，干扰模型对遥感场景的视觉理解与语言对齐能力。研究表明，这类扰动不仅具有更强的环境可实现性，也能在红外遥感任务中显著降低模型的识别、描述与推理表现。该工作揭示了红外视觉语言模型在物理世界攻击面上的新脆弱性，并为后续开展鲁棒训练、传感器防护与对抗检测提供了参考。

来源 arXiv 时间 2026-07-07 16:46:46

真实世界数据复杂性下的大模型数据分析能力评测

这项研究聚焦大语言模型在真实数据分析场景中的表现，而不仅是标准化基准题。作者围绕现实世界数据常见的复杂性——如噪声、缺失值、格式不一致、异常点、混合类型字段以及多步骤推理需求——设计或整理了相应评测框架，用于检验模型在数据理解、清洗、分析与结论生成上的可靠性。研究强调，传统静态基准往往高估了模型能力，难以反映实际工作流中的脆弱性与误差累积。该工作有助于识别大模型在数据分析任务中的优势边界，也为构建更贴近生产环境的评测方法和智能数据工具提供参考。

来源 arXiv 时间 2026-07-07 16:43:05

量子多体系统时间演化预测的可证明学习分离

这篇论文研究如何从有限观测数据中学习量子多体系统的时间演化，并给出一个“可证明的学习分离”结果：对于某些时间演化预测任务，经典学习方法在样本或计算效率上会遭遇根本限制，而利用更合适的量子表征或假设则能够实现有效预测。作者围绕量子多体动力学中的可学习性，分析了模型表达、数据获取与泛化误差之间的关系，揭示了预测未来量子态演化并不只是工程问题，而是与系统结构和学习范式密切相关的理论问题。这一结论对量子模拟、量子控制以及量子机器学习中的动态建模具有参考价值。

来源 arXiv 时间 2026-07-07 16:30:09

WordVoice：面向大模型语音合成的词级多维显式解耦控制

这篇论文提出 WordVoice，一种面向基于大语言模型的文本转语音（TTS）系统的词级控制框架，重点解决语音生成中“想控制但控不准、多个属性互相干扰”的问题。作者将语音可控维度拆解为多个彼此解耦的词级属性，并通过显式建模让用户能够在词语粒度上分别控制语速、韵律、情感或强调等表现方式，而不是依赖粗粒度的整句指令。相比传统方法，WordVoice 更强调可解释性和组合式控制能力，适合需要精细口语化表达的场景，如有声内容制作、虚拟人播报和交互式语音助手。

来源 arXiv 时间 2026-07-07 16:22:59

从投票到智能体协作：面向BioASQ 14b的答案类型感知大模型流水线

本文聚焦 BioASQ 14b 生物医学问答任务，探讨如何依据问题的答案类型，构建更高效的大模型处理流水线。不同于传统依赖简单投票或统一提示词的做法，作者提出将问题按答案形式进行感知式路由，并进一步引入多智能体协作机制，让不同模型或代理分别承担检索、候选生成、证据整合与最终裁决等角色。该方法旨在提升复杂生物医学问题的覆盖率、准确性与可解释性，同时减少单一模型在长链推理和领域术语理解上的偏差。研究体现了从“多模型投票”向“协同式Agent系统”演进的趋势。

来源 arXiv 时间 2026-07-07 16:12:51

代理分析：作为条件编码器运行的视觉语言模型中的定位信号

本文研究视觉语言模型（VLM）在“条件编码器”模式下是否会保留可用于空间定位的内部信号。作者提出分析-by-proxy的视角：虽然模型并非显式训练来输出框或掩码，但在条件生成、理解或约束推理过程中，其表征可能已隐含对象位置与区域边界信息。通过探测不同层级与不同条件设置下的激活，研究揭示VLM中存在稳定的定位线索，并分析这些线索如何受提示词、视觉上下文和任务形式影响。该工作为理解多模态模型的空间感知能力、提升可解释性，以及将VLM用于弱监督定位与开放词汇视觉任务提供了新的依据。

来源 arXiv 时间 2026-07-07 16:11:13