AI News

AcrossVAM2.0: Conflict-Aware Point Supervision for Parameter-Efficient Video Diffusion Adaptation (arxiv.org)

Joint Discrete and SE(3) Diffusion for Protein Interface Design (arxiv.org)

DSABench: Benchmarking Source Discovery, Coordination, and Execution for Multi-Database Agents (arxiv.org)

How to Build a Benchmark That Actually Measures Taste (arxiv.org)

Relational Semantic Grounding for Test-Time Discovery (arxiv.org)

MHWA: Multi-timescale Hierarchical World-Action Model (arxiv.org)

Think in Strategies, Act with Tools: Traceable Agentic Optimization for Combinatorial Problems (arxiv.org)

SAGE: Pushing 2-Bit Vector-Quantized LLMs toward Real-World Usability (arxiv.org)

Equal-information evaluation of credit assignment in modular financial reinforcement learning (arxiv.org)

GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMs (arxiv.org)

CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation (arxiv.org)

Bayesian Learning to Select Fair Classifiers (arxiv.org)

How Should a Camera-First AI Agent Work? (arxiv.org)

Correction Training for Diffusion Models (arxiv.org)

MCMC Can See Can't See (arxiv.org)

Optimizing Sparse Boolean Rule Networks using Mixed Integer Linear Programming (arxiv.org)

MAEM: Mitigating Recency Bias via a Replay-Free, Capacity-Controlled Dynamic Mixture of Experts for Class-Incremental Graph Learning (arxiv.org)

From Plato to Aristotle: Toward a General Theory of Representation Hypotheses (arxiv.org)

SpectrumQuant: Spectrum Alignment for LLM Quantization (arxiv.org)

Hierarchical Gaussian Processes for Survey Weighting: Local Equivalent Weights in Structured Populations (arxiv.org)

Beyond Expert Rankings: Contrast Calibration for Mixed-Precision MoE Quantization (arxiv.org)

Just Respect the Semantics: Image-Token Compression via Pre-LLM Semantic Variable-Resolution Tokenization and In-LLM Relevance Pruning (arxiv.org)

Fractional is Better: Learnable Derivative Orders in Neural Operator Learning (arxiv.org)

When Does Momentum Help in Reinforcement Learning with Verifiable Rewards? (arxiv.org)

Tracking a Small Set of Experts in Online Convex Optimization (arxiv.org)

Testing Conditional Distribution Equality Using Generative Models (arxiv.org)

The Statistical Benefits of Multiple Responses for Learning from Demonstrations (arxiv.org)

Principled Design of Expected Improvement for Continuous Simulation Optimization (arxiv.org)

Bellman Conformal Inference: Calibrating Prediction Intervals For Time Series (arxiv.org)

GLL: A Differentiable Graph Learning Layer for Neural Networks (arxiv.org)

Amortized ratio-estimation importance sampling and localized simulation-based calibration for intractable likelihoods (arxiv.org)

Last Secure Code Benchmark: Is the Code You Vibe Secure? (arxiv.org)

Artificiality's First Exam: An LLM-Referenced C-test for Supraintelligence (arxiv.org)

The Silent Failures in Agentic Data Science (arxiv.org)

ClawLoop: Self-Improving Agents via Harness-Native Training Loop (arxiv.org)

Counterfactual Regret for Reflective Agents with Lean-Verified Guarantees (arxiv.org)

A Decade of PhotoMappers: A Longitudinal Study of Crowdsourced Disaster Photos Geolocalization with Vision-Language Models and Geospatial Reasoning (arxiv.org)

ELECT: Settling Identity Before Rendering for Scalable Story Visualization (arxiv.org)

Dynamic Conflict Clustering with Lightweight Learning and Strategic Repair for Distributed Constraint Satisfaction (arxiv.org)

Rethinking Human Intent-to-CAD: Parametric CAD Model Generation via Cooperative Multi-Task Alignment and Spatial-Aware Reinforcement Learning (arxiv.org)

TabMosaic: Unified In-Context Diffusion for Tabular Generative Tasks (arxiv.org)

RespFocus: Learning Temporal Evidence for Weakly Supervised Respiratory Sound Classification (arxiv.org)

bharatSetu: a 1M x 22 bridge for indic translation (arxiv.org)

What DNA Foundation Models Learn Beyond Sequence Composition (arxiv.org)

Uncovering the Generative Landscape of Diffusion Models: A Spectral-Guided Quality-Diversity Diffusion Framework (arxiv.org)

Embedding Information in Policy Randomness: Distribution-Preserving Implicit Communication in MDPs (arxiv.org)

SkillMarker: A KGW-Based Watermarking Method for Agent Skill Ownership Verification (arxiv.org)

Beyond Time Induction: Structured Conditional Neural Solvers for Parametric Stochastic-Volatility Pricing (arxiv.org)

Exploring Interpretability in Deep Learning-Based Forest Classification - Separating Similar Forest Classes using Sentinel-2 Time Series (arxiv.org)

Outcome-Routed Distillation and Reinforcement Learning for Diffusion Language Models (arxiv.org)