Reverse Preference Optimization for Complex Instruction FollowingAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache ReuseEuropean Conference on Parallel Processing (Euro-Par), 2025 |
GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
ReChisel: Effective Automatic Chisel Code Generation by LLM with ReflectionDesign Automation Conference (DAC), 2025 |