AI News

Conversational Voice Aesthetic Model with Reinforcement Learning from Human Listeners (arxiv.org)

A mesh-based neural energy method for the simulation of heterogeneous composites (arxiv.org)

Enabling Preference-driven Unlearning in Few-step Distilled Text-to-Image Diffusion Models (arxiv.org)

Syn-Omni: Structured Specialization and Progressive Collaboration for Omnimodal Embeddings (arxiv.org)

How Much Audio Is Left In An Embedding? An Inversion Audit Of Audio Encoders (arxiv.org)

Real-Time Motion Planning with Dynamic Hazards: Classical vs. Learning-Based Methods (arxiv.org)

La-Ribo: RNA Co-Design via Geometry-Latent Flow Matching (arxiv.org)

ReSI: Recursive Safety Improvement toward Resistant and Resilient AI (arxiv.org)

Characterizing Overconfident Failure in LLM-Based Code Generation (arxiv.org)

From Prompting to Composing: A Spatial Canvas Interface for Poster Generation (arxiv.org)

VibeEdit: Image Editing with Canvas Instructions (arxiv.org)

AI-Based On-Board Maritime Object Detection for Earth Observation Payload Data Reduction on Versal Embedded Hardware (arxiv.org)

Unifying Policy Learning and State Prediction through Spatial Language Modeling (arxiv.org)

RFChipAgent: Multi-Agentic AI Flow for Analog/RF Chip Design (arxiv.org)

Real Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute (arxiv.org)

Diagnosing and Recovering from Observation-Space Shift at Long-Horizon Skill Seams (arxiv.org)

NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime (arxiv.org)

Strategic Investment Decision Making for Value Creation in Energy Transition: A Reinforcement Learning Approach (arxiv.org)

Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching (arxiv.org)

WOVEN: Weaving Visual World Modeling into Multimodal LLMs (arxiv.org)

Predicting Alignment Generalization with Value Representations (arxiv.org)

Subspace Uncertainty and Sharp Sampling Thresholds on the Boolean Cube (arxiv.org)

VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling (arxiv.org)

All Verdicts are Not Equal: Rethinking LLM Judge Reliability (arxiv.org)

MAST: Motif-Augmented Diffusion with Search Tree for Spectroscopic Molecular Structure Elucidation (arxiv.org)

Traceable World State: A Provenance-Aware State Representation and Deterministic Replay Framework for Robotic Systems (arxiv.org)

Simultaneous Computation with Multiple Prioritizations in Multi-Agent Motion Planning (arxiv.org)

VFold: Symmetry-Aware Cross-Layer Value Cache Compression (arxiv.org)

asdex: Automatic Sparse Differentiation in JAX (arxiv.org)

RiCo: Neural Simulation of Rigid-Body Interactions via Local Contact Reasoning (arxiv.org)

Spatial Pattern Formation from Multi-Agent Learning in Public Goods Dilemmas (arxiv.org)

Humanoid World Action Model With Joint State--Action Generation (arxiv.org)

REACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with VLA Models (arxiv.org)

Neural Network Verification for Deep Joint Source-Channel Coding (arxiv.org)

DataVista: Diagnosing Multimodal LLMs on Data Video Understanding (arxiv.org)

Use and Disuse: Intent-Structured Experience Consolidation for Memory and Learning in LLM Agents (arxiv.org)

Toward Optimal Regret in Adversarial MDPs with Stochastic Hard Constraints (arxiv.org)

Rehearse Everything, Remember Nothing: Attic-KV Rehearses What Will Be Read (arxiv.org)

A structure-preserving neural density functional for the ions of a polymer electrolyte (arxiv.org)

Ambient Discrete Diffusion: Using the Wrong Data at the Right Time for Data Efficient Learning (arxiv.org)

Recompose and Refine Latent Reasoning Flows for Vision-Language-Action Models (arxiv.org)

EvoAlloc: A Self-Evolving Resource Allocation Agent for Efficient Program Evolution (arxiv.org)

Is Memorization Context-Sensitive? Prefix-Based Extraction Beyond Isolated Prefixes (arxiv.org)

When Should Agents Think? Adaptive Reasoning via Cross-Turn Estimation (arxiv.org)

Instruction-Conditioned Electromagnetic Spectrum Understanding via Budget-Adaptive Signal Tokenization (arxiv.org)

Using Weisfeiler-Leman Features for Algorithm Selection in Constraint Optimisation (arxiv.org)

AdaCast: Conditional Parameter Generation for Adaptive Time Series Forecasting (arxiv.org)

A Geometric Approach to Soft Actor-Critic with Zonotopes for Locomotion Learning (arxiv.org)

Few-Step Generation via Data-Space Iteration (arxiv.org)

Q-Shaped Options for Hierarchical Reinforcement Learning (arxiv.org)