 TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation TasksAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
 Accelerating Adaptive Retrieval Augmented Generation via Instruction-Driven Representation Reduction of Retrieval OverlapsAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
 PCM : Picard Consistency Model for Fast Parallel Sampling of Diffusion ModelsComputer Vision and Pattern Recognition (CVPR), 2025 |
 Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine TranslationAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
 Fuzzy Speculative Decoding for a Tunable Accuracy-Runtime TradeoffAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
 TETRIS: Optimal Draft Token Selection for Batch Speculative DecodingAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
