EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation Paper • 2605.23271 • Published 27 days ago • 80
ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactions Paper • 2605.20087 • Published 30 days ago • 18
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Paper • 2605.11609 • Published May 12 • 195
FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching Paper • 2605.20910 • Published 29 days ago • 29
software-mansion/react-native-executorch-whisper-small Automatic Speech Recognition • Updated 8 days ago • 497 • 1
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation Paper • 2604.28196 • Published Apr 30 • 73
Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling Paper • 2604.28075 • Published Apr 30 • 20