AI News

Reinforcement Learning via Advantage Guidance (arxiv.org)

Learning Who Benefits Most: Multi-Treatment Causal Ranking for Population Health Stratification (arxiv.org)

Posterior Flow Matching (arxiv.org)

North or South? Diagnosing LLMs' Understanding of North Korean Language, Society, and Knowledge (arxiv.org)

GeoBridge: Evolving Transferable Decoder Topologies for Geometric Vision (arxiv.org)

Online Tokenization with Optimal Delay in Linear Time (arxiv.org)

From Copying to Composition: How Language Models Develop In-Context Learning (arxiv.org)

CTIA-ODE: Continuous-Time Inter-Variable Attention for Long-Term Time Series Forecasting (arxiv.org)

LeHami: Symplectic Latent Dynamics for World Models (arxiv.org)

Sequent-Prover: Training Agents for Formal, Checkable SMT-based Reasoning (arxiv.org)

EvolvAttack: Backdooring self Evolving VLM Agents (arxiv.org)

Framework for an AI-Ready ARPES Community Database (arxiv.org)

PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces (arxiv.org)

Exploring Jailbreak Vulnerability Across Depth-Based Dynamic Inference in Large Language Models (arxiv.org)

UDHRBench: Benchmarking Human Rights in Large Language Models (arxiv.org)

To Defer or Not to Defer? Online Learning with LLMs and Congested Experts (arxiv.org)

RIECNN: Real-Time Image Enhanced CNN for Traffic Sign Recognition (arxiv.org)

AlignMerge - Alignment-Preserving Large Language Model Merging via Fisher-Guided Geometric Constraints (arxiv.org)

Alignment Faking - the Train -> Deploy Asymmetry: Through a Game-Theoretic Lens with Bayesian-Stackelberg Equilibria (arxiv.org)

Multi-agent Undercover Gaming: Hallucination Removal via Counterfactual Test for Multimodal Reasoning (arxiv.org)

Knowledge Graphs as Files: An Agent Harness Where Tool Creation and Tool Use Co-Evolve (arxiv.org)

Does self-distillation improve reasoning? (arxiv.org)

Nudge the Judge: Uncovering Program Decision Hijacking in Real-World Jev Applications (arxiv.org)

Jev-ToM: Evaluating Theory of Mind in Typed Decision Models (arxiv.org)

DPOison-VL: Clean Preference Poisoning in Vision-Language Direct Preference Optimization (arxiv.org)

Model-Based Online Decision Making via Generative Trajectory Planning (arxiv.org)

Rethinking Projector Training in Multimodal LLMs (arxiv.org)

PhysicsSliders: Learning Physical Controls for Audio Foley Generation (arxiv.org)

ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models (arxiv.org)

GeoMER: A Joint Euclidean-Hyperbolic Geometry Framework for Multimodal Emotion Recognition (arxiv.org)

Falsification-proof non-market allocation mechanisms (arxiv.org)

When More Objectives Make Identification Easier: The Role of Preferences and Feedback (arxiv.org)

The Many Morals of AI: The cautionary bias of North American news narratives in global perspective (arxiv.org)

On Symmetry for Characterizing Agent Heterogeneity in Multi-Agent Systems (arxiv.org)

APTree: Extended Behavior Trees for Adaptive and Scalable Automated Robotic Task Planning in Construction (arxiv.org)

LLM2R: From Large Language Models to 3D Reassemblers (arxiv.org)

The Geometry of Language Model Logits: Generic Structure and Learned Departures (arxiv.org)

A Global View of How LLMs Value Human Time (arxiv.org)

Better Capturing Interactions Between Products in~Retail: Revisited Negative Sampling for~Basket Choice Modeling (arxiv.org)

When Missingness Follows the Graph: Beyond Feature Propagation for Missing Features (arxiv.org)

A CaLLM Judge is a Better Judge: Mitigating Bias in LLM-as-a-judge (arxiv.org)

APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation (arxiv.org)

Uncertainty Evaluation: Bridging Machine Learning and Measurement Science (arxiv.org)

Lifting Finite-Sample Gaussian Approximation of Wide Neural Networks to Functional Convergence (arxiv.org)

From Policy Evaluation to Off-Policy Control: Provable Emergence of In-Context Q-Learning (arxiv.org)

Fan Out or Relay? Ownership-Aware Routing for LLM Agents Querying Siloed Tables (arxiv.org)

inLoRA-MINT: Internal Representations for Auditing Training Data in Domain-adapted LLMs (arxiv.org)

High-fidelity Three-Dimensional Flow Field Reconstruction Driven by Turbulent Fluid Dynamics (arxiv.org)

Can Machine Learning Potentials Be More Accurate Than the Methods They Are Trained On? (arxiv.org)

ChampionKV: Head-Wise Adaptive Budget Allocation for KV Cache Compression (arxiv.org)