Yicheng Ji, Jun Zhang 0069, Heming Xia, Jinpeng Chen 0001, Lidan Shou, Gang Chen 0001, Huan Li 0003. SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning. In Christos Christodoulopoulos 0001, Tanmoy Chakraborty 0002, Carolyn Rose, Violet Peng, editors, Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, EMNLP 2025, Suzhou, China, November 4-9, 2025. pages 7205-7219, Association for Computational Linguistics, 2025. [doi]
Abstract is missing.