3 papers
cs.CL2026
Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning
Yanyu Zhu, Hoilam Pao, Niu Hu +6
Large Language Models suffer from slow autoregressive inference. While self-speculative decoding accelerates this process, its efficiency is hampered by static configurations like…
cs.CL2025
FEANEL: A Benchmark for Fine-Grained Error Analysis in K-12 English Writing
Jingheng Ye, Shen Wang, Jiaqi Chen +9
Large Language Models (LLMs) have transformed artificial intelligence, offering profound opportunities for educational applications. However, their ability to provide fine-grained…
cs.CV2025
Removing Averaging: Personalized Lip-Sync Driven Characters Based on Identity Adapter
Yanyu Zhu, Lichen Bai, Jintao Xu +1
Recent advances in diffusion-based lip-syncing generative models have demonstrated their ability to produce highly synchronized talking face videos for visual dubbing. Although the…