AI News

The Reliability Gap in Benchmark Auditing: Distribution Shift and Scale as Failure Modes of Contamination Detection (arxiv.org)

A formal definition and meta-model for a machine theory of mind (arxiv.org)

Self-Soupervision: Cooking Model Soups without Labels (arxiv.org)

Sign Lock-In: Randomly Initialized Weight Signs Persist and Bottleneck Sub-Bit Model Compression (arxiv.org)

A Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs and Knowledge Graphs (arxiv.org)

PieArena: Ranking and Profiling Language Agents in Realistic Negotiation Scenarios (arxiv.org)

Toward a Modular Architecture for Embedded AI Agent Systems at the Edge (arxiv.org)

Low-Frequency Shortcuts in Texture-Driven Visual Learning (arxiv.org)

Typhoon: Towards an Effective Task-Specific Masking Strategy for Pre-trained Language Models (arxiv.org)

Plan, Verify and Fill: A Structured Parallel Decoding Approach for Diffusion Language Models (arxiv.org)

Thinking Past the Answer: Evaluating Harmful Overthinking in Large Reasoning Models (arxiv.org)

Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation (arxiv.org)

Correcting Neural Operator Spectral Bias via Diffusion Posterior Sampling with Sparse Observations (arxiv.org)

Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early Detection (arxiv.org)

Testing the Test: Score-Direction Instability in Class-Split Anomaly Detection (arxiv.org)

SketchSong: Hierarchical Song Generation with Sketch Planning and Fine-Grained Multi-Track Modeling (arxiv.org)

Spatial Transcriptomics-Guided Alignment Enhances Molecular Profiling in Pathology Foundation Model (arxiv.org)

Causal Preference Elicitation (arxiv.org)

Echo-POSED: Geometric Self-Distillation for Echocardiography Guidance (arxiv.org)

A Scoping Review of the Ethical Perspectives on Anthropomorphising Large Language Model-Based Conversational Agents (arxiv.org)

Aligning Data-Driven Predictors with Allocation: A Decision-Focused Approach to Survival Analysis (arxiv.org)

Visual Graph Scaffolds for Structural Reasoning in Large Language Models (arxiv.org)

Building Better Activation Oracles (arxiv.org)

ReLoRA: Knowledge-Reusing Adaptation for Fast Rollout of Evolving LLM Services (arxiv.org)

Cross-Modal Contrastive Learning of ECG and Angiography Representations for Severe Stenosis Classification (arxiv.org)

ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning (arxiv.org)

ChatHealthAI: Aligning Electronic Health Record Representations with Large Language Models for Grounded Clinical Reasoning (arxiv.org)

Geometry-Aware Tabular Diffusion (arxiv.org)

Auditable Climate Risk Intelligence from Fragmented ESG Data: Deterministic Orchestration and Imbalance-Aware Learning for Scope 1-3 Validation (arxiv.org)

Improvise, Adapt, Overcome: An On-The-Fly Multifidelity Algorithm for Efficient Machine Learning (arxiv.org)

Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs (arxiv.org)

Evaluating Transformer and LSTM Frameworks for Prediction in Ungauged Basins (arxiv.org)

PerchRL: Vision-Based Agile Perching on Inclined Platforms under Rapid and Irregular Motion (arxiv.org)

AdaWeather: Adaptively Mixing Probabilistic Weather Forecasts with Logarithmic Regret (arxiv.org)

Sample-Size Scaling of the African Languages NLI Evaluation (arxiv.org)

Assessing Region-Level EEG Contributions to Cognitive Workload Prediction (arxiv.org)

Graph Mamba Survival Analysis Based on Topology-Aware ordering (arxiv.org)

AURA: Action-Gated Memory for Robot Policies at Constant VRAM (arxiv.org)

BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces (arxiv.org)

Making Brain-Computer Interfaces More Secure (arxiv.org)

How Visible Are Silent Manipulation Failures? An Observability Study of False-Success Detection in Simulated Robot Episodes (arxiv.org)

PyraMathBench: Evaluating and Improving Mathematical Capability in Large Language Models (arxiv.org)

NeuroArmor: Safe-Variant-Guided Representation Consistency for Selective Re-Anchoring in Jailbreak Defense (arxiv.org)

The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size (arxiv.org)

Reasoning Structure of Large Language Models (arxiv.org)

Regime-Arrival Uncertainty in Generalization Bounds under Distribution Shift (arxiv.org)

Before Fusion, Ask What to Keep: Contextual Calibration of Multimodal Signals (arxiv.org)

Locality Does Not Imply Reachability: Boundary Repair in Block-Sparse Causal Attention (arxiv.org)

Generalizing Graph Foundation Models via Hyperbolic Retrieval-Augmented Generation (arxiv.org)

Critical evaluation of PINN for FWD inverse analysis and differentiable FEM as an alternative (arxiv.org)