Publications

A selection, by theme. For the full list, see Google Scholar.

Efficiency in large models

Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling
Yongchang Hao, Lili Mou
ICLR 2026 · Rio de Janeiro, Brazil
Paper Code
Radar: Fast Long-Context Decoding for Any Transformer
Yongchang Hao, Mengyao Zhai, Hossein Hajimirsadeghi, Sepidehsadat Hosseini, Frederick Tung
ICLR 2025 · Singapore
Paper Code
NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks
Yongchang Hao, Yanshuai Cao, Lili Mou
ENLSP @ NeurIPS 2024 · Vancouver, Canada
Paper Code
Flora: Low-Rank Adapters Are Secretly Gradient Compressors
Yongchang Hao, Yanshuai Cao, Lili Mou
ICML 2024 · Vienna, Austria
Paper Code

VEG: Verbal ε-greedy for Semantic Exploration in Multi-Turn RL Agents
Yongchang Hao, Jie Hao, Yongsheng Mei, Ze Ye, Junyi Chai, Bin Guo, Benjamin Z. Yao, Chenlei Guo, Lili Mou
ACL 2026 (Industry Track) · San Diego, United States
Paper
Teacher Forcing Recovers Reward Functions for Text Generation
Yongchang Hao, Yuxin Liu, Lili Mou
NeurIPS 2022 · New Orleans, United States
Paper Code