Hao, Jitai

3 publications

ICLR 2026 Uni-X: Mitigating Modality Conflict with a Two-End-Separated Architecture for Unified Multimodal Models Jitai Hao, Hao Liu, Xinyan Xiao, Qiang Huang, Jun Yu

NeurIPS 2025 A Token Is Worth over 1,000 Tokens: Efficient Knowledge Distillation Through Low-Rank Clone Jitai Hao, Qiang Huang, Hao Liu, Xinyan Xiao, Zhaochun Ren, Jun Yu

ICLR 2025 OmniKV: Dynamic Context Selection for Efficient Long-Context LLMs Jitai Hao, Yuke Zhu, Tian Wang, Jun Yu, Xin Xin, Bo Zheng, Zhaochun Ren, Sheng Guo