AI News

TraceRelay: Attention-Aligned Recurrence over Rolling Traces (arxiv.org)

Correlational Training of Morphological Neural Networks (arxiv.org)

Uncovering and Fixing Collider Bias in Bayesian PINNs (arxiv.org)

Timer-M1: A Multivariate Time Series Foundation Model via Learning Primitives (arxiv.org)

MSGAT: Multi-Head Spiking Graph Attention with Similarity-Space Fusion for Image-Text Retrieval (arxiv.org)

Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games (arxiv.org)

Lamarck's Driving School: Discovering Autonomous Driving Training Strategies through Evolutionary Competition (arxiv.org)

Evidence-Traceable Dynamic Interviewer Architecture for Expertise-Adaptive Qualitative Interviews Using Local LLMs (arxiv.org)

Where to Adapt Matters: Layer-Selective Fine-Tuning for Capability Retention (arxiv.org)

Constitutional Gating and Deterministic Recovery for Multi-Agent LLM Negotiation: Ablations Against a Stateful Adversarial Gatekeeper (arxiv.org)

Rewiring Semantics, Dynamics, and Control: A Simple yet Effective Action-Centric Tri-Stream Transformer (arxiv.org)

IndustrialVLA-Bench: A Traceable Multi-Axis Evaluation of Open Robot Policy Models (arxiv.org)

Addressing Overcommitment in the Reasoning of Gendered Economic Memes under Multimodal Ambiguity (arxiv.org)

4-Tensor Attention Model for Semantic Physical Reality (arxiv.org)

Does an Illumination Prior Help Face-Swap Detection? A Controlled Study of Temporal Self-Blended Images (arxiv.org)

What is the goal of unsupervised machine learning? (arxiv.org)

Can Jev be Your Q or Policy in Reinforcement Learning? (arxiv.org)

Puffin: Probabilistic Learning of Spatial Detail From Coarse Observations (arxiv.org)

AgentEvolver: System-Wide Self-Evolution Through Task Execution (arxiv.org)

Error-Propagation Modeling for Failure Attribution in LLM-Based Multi-Agent Systems (arxiv.org)

Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies (arxiv.org)

Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals (arxiv.org)

Self-Supervised Speech Representations for Cross-Speaker Dysarthria Detection During Awake Craniotomy (arxiv.org)

MC-TRCM: Observation-Aware Recursive Fusion for Incomplete Mobile and Wearable Mental-Health Feature Views (arxiv.org)

Learning from Hetero Density for Cryo-EM Protein Reconstruction (arxiv.org)

CoPoE: Multimodal Fusion via Decomposable Disease-Coordinate Product-of-Experts for Missing-Modality Alzheimer's Diagnosis (arxiv.org)

From a Prompt to Repertoires: Evolving Functional REpertoires Enable LLM Continual Learning (arxiv.org)

SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces (arxiv.org)

Recovery Guarantees for Posterior Sampling of One-Bit Compressed Sensing (arxiv.org)

Workerville: Towards an Organizational Behavior Account of Agent Safety (arxiv.org)

Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds (arxiv.org)

ReTeach: Building a Self-Teacher through Multi-Round Reflection and Retry (arxiv.org)

AtomWorld-Mirror: Macro-Step World Modeling of Critical Evolution Backbones for Materials Dynamics (arxiv.org)

LVS: Local View Synthesis from Relative Camera Pose by Reusing Previous Views (arxiv.org)

The Operator Mismatch Problem: Deploying BEV Perception with Portable GPU Compute (arxiv.org)

Pretext: Defeating Malicious Skill Detection Frameworks for AI Agents (arxiv.org)

Fed-GRPO: Reward-Signal-Driven Federated Group Relative Policy Optimization (arxiv.org)

BridgeGuard: Explicit Safety Drift for Diffusion-based Autonomous Driving (arxiv.org)

From Chain-of-Thought to Loops: Non-Autoregressive Latent Reasoning via Looped Transformers (arxiv.org)

The Score Is Not the Structure: Brain Alignment and Cross-Lingual Transfer (arxiv.org)

Bernoulli Flow Models: Self-Consistent Generative Modeling for Binary Data (arxiv.org)

Deflating the Hessian: Rank-4 W4A4 Quantization for Multimodal Diffusion Transformers (arxiv.org)

NP-Hardness of Minimizing Neurons in Two-Hidden-Layer ReLU Neural Networks (arxiv.org)

Memorization and Malign Generalization in Conditional Diffusion Models with Random Features (arxiv.org)

How to post-train on a surrogate: Envelope sampling mitigates reward hacking (arxiv.org)

Learning to Orchestrate Evolutionary Search: Progression-Aware Deep Reinforcement Learning for Dynamic DE-CMA-ES Coordination in Optimization and Structural Model Updating (arxiv.org)

Scaling Verifiable Environments for Long-horizon Work Agents (arxiv.org)

Population Scaling or Data Dilution? Dynamics of Local Topology Evolution in Decentralized Learning (arxiv.org)

SpikeSSL: A Universal Spike Inference Framework with Dynamics-Informed State-Space Layers (arxiv.org)

New Lower Bound and Upper Bounds on the Regret for Online Sparse Linear Regression (arxiv.org)