DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards Paper • 2605.21467 • Published 4 days ago • 190
japanese-asr/whisper_transcriptions.reazon_speech_all Viewer • Updated Sep 14, 2024 • 17.3M • 423k • 9
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence Paper • 2605.12882 • Published 11 days ago • 262
Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs Paper • 2604.05643 • Published Apr 7 • 13
Adam's Law: Textual Frequency Law on Large Language Models Paper • 2604.02176 • Published Apr 2 • 503
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models Paper • 2604.08546 • Published Apr 9 • 115
Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation Paper • 2604.03118 • Published Apr 3 • 6