6 papers
FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models
Haoyu Huang, Linlin Yang, Sheng Xu +5
Diffusion Large Language Models (dLLMs) refine tokens iteratively but commit them irreversibly, leading to a "stability lag" where early decisions remain fragile even after being w…
SURGE: Surrogate Gradient Adaptation in Binary Neural Networks
Haoyu Huang, Boyu Liu, Linlin Yang +6
The training of Binary Neural Networks (BNNs) is fundamentally based on gradient approximation for non-differentiable binarization operations (e.g., sign function). However, prevai…
An Empirical Study of World Model Quantization
Zhongqian Fu, Tianyi Zhao, Kai Han +3
World models learn an internal representation of environment dynamics, enabling agents to simulate and reason about future states within a compact latent space for tasks such as pl…
EAQuant: Enhancing Post-Training Quantization for MoE Models via Expert-Aware Optimization
Zhongqian Fu, Tianyi Zhao, Ning Ding +4
Mixture-of-Experts (MoE) models enable scalable computation and performance in large-scale deep learning but face quantization challenges due to sparse expert activation and dynami…
Efficiently Seeking Flat Minima for Better Generalization in Fine-Tuning Large Language Models and Beyond
Jiaxin Deng, Qingcheng Zhu, Junbiao Pang +3
Little research explores the correlation between the expressive ability and generalization ability of the low-rank adaptation (LoRA). Sharpness-Aware Minimization (SAM) improves mo…
GPT4Image: Large Pre-trained Models Help Vision Models Learn Better on Perception Task
Ning Ding, Yehui Tang, Zhongqian Fu +3
The upsurge in pre-trained large models started by ChatGPT has swept across the entire deep learning community. Such powerful models demonstrate advanced generative ability and mul…