Speculative decoding accelerates memory-bound LLM decoding with a lightweight drafter, and parallel drafters extend this speedup by drafting a whole block in one forward pass. However, it remains unclear whether their released systems (stock) attain the full speedup that parallel drafting permits. We identify three cha...
Kun-Jun Li, Wen-Hao Chai, Yihao Liang et al.· 0 citations
Red-TTT is proposed, which updates the attacker's parameters during the attack on each behavior, and requires only sampling access to the victim and integrates into existing attack pipelines with no other changes, increasing attack success rate and cracking many behaviors previous method cannot.
Tong-Yan Hu, Hao Li, Xiaogeng Liu et al.· 0 citations
Negative Self-Distillation (NSD) is introduced, a new framework that optimizes LLMs by diverging from flawed reasoning rather than imitating privileged solutions, and consistently outperforms OPSD and other label-free, self-bootstrapping reinforcement learning (RL) baselines.
Rong-Can Pei, Zhepei Wei, Shu-Yao Xu et al.· 1 citation
This work introduces CutCraft, the first benchmark for editing-technique execution in multi-shot audio-video generation and designs an agentic editing baseline that decomposes generation into planning, shot-level synthesis, and post-hoc composition, explicitly realizing editing semantics such as J-cuts, L-cuts, and tra...
Tian-Yi Zeng, Junchao Liao, Yu-Jie Wei et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.