14 papers
Post-Training Pruning for Diffusion Transformers
Chengzhi Hu, Xuewen Liu, Jing Zhang +3
The paper introduces DiT-Pruning, a post‑training pruning method tailored for Diffusion Transformers that uses a new energy‑based saliency metric and clustering‑aware granularity t…
OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization
Zhikai Li, Zhen Dong, Xuewen Liu +2
Large Language Models (LLMs) have demonstrated remarkable capabilities. However, their massive parameter scale leads to significant resource consumption and latency during inferenc…
Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models
Zhikai Li, Yue Zhao, Edward Zhongwei Zhang +4
Reinforcement learning from human feedback (RLHF) effectively promotes preference alignment of text-to-image (T2I) diffusion models. To improve computational efficiency, direct pre…
QFT: Quantized Full-parameter Tuning of LLMs with Affordable Resources
Zhikai Li, Xiaoxuan Liu, Banghua Zhu +3
Large Language Models (LLMs) have showcased remarkable impacts across a wide spectrum of natural language processing tasks. Fine-tuning these pretrained models on downstream datase…
Sparsity Induction for Accurate Post-Training Pruning of Large Language Models
Minhao Jiang, Zhikai Li, Xuewen Liu +3
Large language models have demonstrated capabilities in text generation, while their increasing parameter scales present challenges in computational and memory efficiency. Post-tra…
K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge
Zhikai Li, Jiatong Li, Xuewen Liu +7
The rapid development of visual generative models raises the need for more scalable and human-aligned evaluation methods. While the crowdsourced Arena platforms offer human prefere…