AI News

Distribution Matching Evolutionary Algorithms for Rare Event Sampling (arxiv.org)

MoLE: Mixture of Latent Experts for Complementary Visual Reasoning (arxiv.org)

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

OmniCam: Omni-Camera Trajectory Generation via Geometry-Grounded Pose Token Learning (arxiv.org)

ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text Editing (arxiv.org)

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

Ready2Blend: From Natural-Language Instructions to Composable Alignment Prompts (arxiv.org)

Structure vs. Chain-of-Thought: Evaluating LLM Criteria Extraction for Depression Severity (arxiv.org)

On the Relaxation of Conditional Independence Assumption for Image Segmentation (arxiv.org)

Why Software Engineering Is Indispensable in the Age of Coding Agents (arxiv.org)

Purlin: Separating Orchestration from the Datapath of Collectives (arxiv.org)

WeLike2Party! In-Context Motion Transfer for Multi-Human Image Animation (arxiv.org)

Proofs Without Nominals: G\"odel's Ontological Argument, its Shallow Embedding, and the Open Questions of the Monatshefte Notes (arxiv.org)

Draft in Parallel, Condition Through Depth: Adjacent Causal Injection for Speculative Decoding (arxiv.org)

V-JEPA Policy: Building Effective World-Action Models on Predictive Visual Latents (arxiv.org)

The Compiler May Read It, the Agent May Not: Keeping Part of a Research Code Away from a Coding Agent (arxiv.org)

ESTHER: Egocentric Stereo Hand Estimation and Reconstruction in the Wild (arxiv.org)

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

Eval4DiRec: A Unified and Systematic Evaluation Framework for Diffusion-based Recommender Systems (arxiv.org)

LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations (arxiv.org)

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

SoFT: Soft Targets for Generalizable LLM Fine-Tuning (arxiv.org)

Verification as an Architectural Layer for LLM Agents: A V-Model Design, and a Pilot Study of Its Deterministic Core (arxiv.org)

From Chasing Ghosts to Missed Attacks: Perspectives and Perceptions of SOC Practitioners on LLM Integration, Risks, and Readiness (arxiv.org)

Do Factuality Methods Make LLMs More Factual? Reproducibility and Fair Comparison (arxiv.org)

MS-Exam-Gen: An Automatic Benchmark Construction Toolkit for Evaluating LLMs on Multiple Sclerosis-MRI Imaging Knowledge (arxiv.org)

Do More Modalities Always Help? A Geometric Perspective on Missing-Modality Robustness (arxiv.org)

Does self-distillation improve reasoning? (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)

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

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

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

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

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

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

ROI-Reasoning: Rational Optimization for Inference via Pre-Computation Meta-Cognition (arxiv.org)

GDEPO: Group Dual-dynamic and Equal-right Advantage Policy Optimization for Sample-Efficient Reinforcement Learning (arxiv.org)

Stochastic CHAOS: Why Deterministic Inference Kills, and Distributional Variability Is the Heartbeat of Artifical Cognition (arxiv.org)

Risky-Bench: Evaluating Agentic Safety Risks in Real-World Life-Assist Deployments (arxiv.org)

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

Simple Baselines are Competitive with Code Evolution (arxiv.org)

Agentic Architect: An Agentic AI Framework for Architecture Design Exploration and Optimization (arxiv.org)

OracleProto: A Reproducible Framework for Benchmarking LLM Forecasting via Knowledge Cutoffs and Temporal Masking (arxiv.org)

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

Aligning Faithfulness for Theory-Scale Autoformalization (arxiv.org)

PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution (arxiv.org)

On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning (arxiv.org)

Penumbra: Sample-Efficient Adversarial Search for Regulatory Obligations (arxiv.org)

Recursive Improvement of a Differentiable Scientific Software Ecosystem (arxiv.org)