3 papers
cs.CV2026
Timestep-Aware Block Masking for Efficient Diffusion Model Inference
Haodong He, Yuan Gao, Weizhong Zhang +1
Diffusion Probabilistic Models (DPMs) have achieved great success in image generation but suffer from high inference latency due to their iterative denoising nature. Motivated by t…
cs.LG2025
Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient
Yuan Gao, Zujing Liu, Weizhong Zhang +2
Recent Large-Language Models (LLMs) pruning methods typically operate at the post-training phase without the expensive weight finetuning, however, their pruning criteria often rely…
cs.LG2024
Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost
Yuan Gao, Weizhong Zhang, Wenhan Luo +4
We aim at exploiting additional auxiliary labels from an independent (auxiliary) task to boost the primary task performance which we focus on, while preserving a single task infere…