LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning Paper • 2606.01336 • Published 3 days ago • 2
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation Paper • 2605.23271 • Published 12 days ago • 79
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Paper • 2605.11609 • Published 22 days ago • 195
FFAvatar: Few-Shot, Feed-Forward, and Generalizable Avatar Reconstruction Paper • 2605.15320 • Published 20 days ago • 7
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence Paper • 2605.12882 • Published 21 days ago • 269
G-Zero: Self-Play for Open-Ended Generation from Zero Data Paper • 2605.09959 • Published 23 days ago • 17
jackf857/qwen3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-5-margin-log Viewer • Updated May 1 • 661 • 40 • 1
Dual-View Training for Instruction-Following Information Retrieval Paper • 2604.18845 • Published Apr 20 • 11
GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents Paper • 2604.07429 • Published Apr 8 • 121