Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models Paper • 2604.10949 • Published 3 days ago • 36
ViVa: A Video-Generative Value Model for Robot Reinforcement Learning Paper • 2604.08168 • Published 7 days ago • 17
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published 8 days ago • 309
Adam's Law: Textual Frequency Law on Large Language Models Paper • 2604.02176 • Published 14 days ago • 470
Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies Paper • 2604.00830 • Published 14 days ago • 15
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models Paper • 2604.08546 • Published 7 days ago • 112
SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise Paper • 2602.12783 • Published Feb 13 • 216
Ghost-FWL: A Large-Scale Full-Waveform LiDAR Dataset for Ghost Detection and Removal Paper • 2603.28224 • Published 16 days ago • 5