AI News

ContractRL: Shielded Group-Relative Policy Optimization for Auditable Tool-Call Repair (arxiv.org)

LEGO-OPD: Factorized Teacher Composition for Multimodal On-Policy Distillation (arxiv.org)

IrekoGPT: Turning Structured Pruning into Post-Hoc Slimmable LLMs (arxiv.org)

FERPO: Forward Entropy-Regularized Policy Optimization (arxiv.org)

Cost-augmented Schr\"odinger bridges on graphs are exactly solvable: a Feynman-Kac tilt replaces learned control (arxiv.org)

The Missing Primitive: Diagnosing and Repairing Mathematical Reasoning in Large Language Models (arxiv.org)

Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning (arxiv.org)

pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows (arxiv.org)

Four Ways to Grow a Classifier and Why One of Them Cannot Learn (arxiv.org)

STARS: From Spatiotemporal Dynamics to Social Representations in Human-Robot Interaction (arxiv.org)

BalLOT: Balanced $k$-means clustering with optimal transport (arxiv.org)

Provable FDR Control for Deep Feature Selection: Deep MLPs and Beyond (arxiv.org)

Neural network-driven domain decomposition for efficient solutions to the Helmholtz equation (arxiv.org)

Iterative Topic Taxonomy Induction with LLMs: A Case Study of Electoral Advertising (arxiv.org)

Moloch's Bargain: Emergent Misalignment When LLMs Compete for Audiences (arxiv.org)

Better Convergence Guarantees for Sign-Based Momentum Methods (arxiv.org)

Less is more: error-distance scaling relation for data-efficient kilometer-scale downscaling of extreme heat (arxiv.org)

Learning Social Navigation from Internet Videos in the Policy State Space (arxiv.org)

FineART: Fine-Grained Annotated Robotic Trajectory Dataset and Vision-Language-Action Model for Bimanual Manipulation (arxiv.org)

MERID: Multimodal Exploration via Recursive Self-Improvement Agents for Major Depression Analysis (arxiv.org)

Amadeus: When Models of People Meet (arxiv.org)

Unbiased Top-$k$ Estimation for On-Policy Distillation (arxiv.org)

Jev in Medicine: A Benchmark Evaluation (arxiv.org)

Convergent Plug-and-Play Image Restoration with Annealed Noise Levels (arxiv.org)

Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction (arxiv.org)

Compressing History into Memory: Distilling Transformers into Recurrent Transformers (arxiv.org)

Deep Symmetric Autoencoders from the Eckart-Young-Schmidt Perspective (arxiv.org)

UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models (arxiv.org)

CHORDONOMICON: A Dataset of 666,000 Songs and their Chord Progressions (arxiv.org)

A framework for auditing grounding claims (arxiv.org)

Token Space: A Category Theory Framework for AI Computations (arxiv.org)

How many labelers do you have? A closer look at gold-standard labels (arxiv.org)

Fenchel Tilting: Weighted Correction for Efficient Finetuning of Generative Models (arxiv.org)

Markovian Dynamics Enforcer: Feasibility Preserving Correction on Learned Dynamics Manifolds (arxiv.org)

TopTimeNet: Topologically-assisted time-series classification model (arxiv.org)

AdaptManip: Learning Adaptive Whole-Body Object Lifting and Delivery with Online Recurrent State Estimation (arxiv.org)

Autoregressive Drillhole Modelling Under Distribution Shift (arxiv.org)

RiboUnmix: Learning Shared Translational Dynamics from Biased and Noisy Ribo-seq Measurements (arxiv.org)

RW-Flow: One-Step Generation on Compact Manifolds via Wasserstein Gradient Flows (arxiv.org)

Learning to Explain While Planning: Rule-Aligned Diffusion Planning for Autonomous Driving (arxiv.org)

Trust the Critic More (arxiv.org)

Sharp Stationary Gaussian Approximation for Constant-Stepsize SGD (arxiv.org)

scTrilemma: Balancing Identity, Invariance, and Fidelity in Single-Cell Representation Learning (arxiv.org)

Blackboard Intelligence Can Surpass Autoregressive on Globally Constrained Problems (arxiv.org)

Capabilities Ain't All You Need: Measuring Propensities in AI (arxiv.org)

Why GRPO Needs Normalization: A Local-Curvature Perspective on Adaptive Gradients (arxiv.org)

QATFactory: A Versatile, Deployment-Aligned Framework for Quantization-aware Training and Distillation of LLMs (arxiv.org)

Explainability of Complex AI Models with Correlation Impact Ratio (arxiv.org)

Poincar\'e Meets Bellman: Revisable Memory, Operational Quotients, and Evidence-Supported Learning in Changing Environments (arxiv.org)

Which LLM to pick? Online Active Model Selection for Large Language Models (arxiv.org)