DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation Paper • 2607.26811 • Published 4 days ago • 88
CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition Paper • 2607.25294 • Published 5 days ago • 43
SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue Paper • 2605.30993 • Published May 29 • 62
Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question Answering Paper • 2605.29648 • Published May 28 • 10
Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding Paper • 2605.20104 • Published May 19 • 7