2026 arXiv dVoting: Fast Voting for dLLMs Sicheng Feng, Zigeng Chen , Xinyin Ma , and 2 more authors arXiv, 2026 arXiv WEB Code arXiv dMoE: dLLMs with Learnable Block Experts Sicheng Feng, Zigeng Chen , Gongfan Fang , and 2 more authors arXiv, 2026 arXiv WEB Code ICLR RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning Sicheng Feng†, Kaiwen Tuo† , Song Wang , and 3 more authors ICLR, 2026 arXiv WEB Code Dataset 机器之心 TMLR When Tokens Talk Too Much: A Survey of Multimodal Long-Context Token Compression across Images, Videos, and Audios Kele Shao† , Keda Tao† , Kejia Zhang , and 7 more authors TMLR, 2026 arXiv Code CVPR Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps Sicheng Feng†, Song Wang† , Shuyi Ouyang , and 5 more authors CVPR, 2026 arXiv WEB Code Dataset 量子位 TMLR Is Oracle Pruning the True Oracle? Sicheng Feng, Keda Tao , and Huan Wang* TMLR, 2026 arXiv WEB Code 2025 TMLR Efficient Reasoning Models: A Survey Sicheng Feng, Gongfan Fang , Xinyin Ma , and 1 more author TMLR, 2025 arXiv Code 2024 Cell Discov. Unveiling potential threats: backdoor attacks in single-cell pre-trained models. Sicheng Feng, Siyu Li , Luonan Chen* , and 1 more author Cell Discovery, (Q1 TOP, IF=14.8) , 2024 WEB PDF Code 测序中国
Dataset 
