11 papers
LoopREG: Representation Supervision Enables Test-Time Recurrent Depth in Diffusion Transformers
Zipeng Wang, Anping Xiong, Jing Zhang +17
Reusing Transformer blocks offers a way to increase diffusion-model computation at test time, but naive recurrence can degrade generation beyond its training depth. We introduce Lo…
Post-Training Pruning for Diffusion Transformers
Chengzhi Hu, Xuewen Liu, Jing Zhang +3
Diffusion Transformers (DiTs) have demonstrated impressive performance in image generation but suffer from substantial computational overhead and resource consumption. Post-trainin…
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…
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…
Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval
Jing Zhang, Zhikai Li, Xuewen Liu +1
Segment Anything Model 2 (SAM2) shows excellent performance in video object segmentation tasks; however, the heavy computational burden hinders its application in real-time video p…
PTQ4ARVG: Post-Training Quantization for AutoRegressive Visual Generation Models
Xuewen Liu, Zhikai Li, Jing Zhang +2
AutoRegressive Visual Generation (ARVG) models retain an architecture compatible with language models, while achieving performance comparable to diffusion-based models. Quantizatio…
Rectified SpaAttn: Revisiting Attention Sparsity for Efficient Video Generation
Xuewen Liu, Zhikai Li, Jing Zhang +2
Diffusion Transformers dominate video generation, but the quadratic complexity of attention computation introduces substantial latency. Attention sparsity reduces computational cos…
SAQ-SAM: Semantically-Aligned Quantization for Segment Anything Model
Jing Zhang, Zhikai Li, Chengzhi Hu +2
Segment Anything Model (SAM) exhibits remarkable zero-shot segmentation capability; however, its prohibitive computational costs make edge deployment challenging. Although post-tra…
Privacy-Preserving SAM Quantization for Efficient Edge Intelligence in Healthcare
Zhikai Li, Jing Zhang, Qingyi Gu
The disparity in healthcare personnel expertise and medical resources across different regions of the world is a pressing social issue. Artificial intelligence technology offers ne…
RepQuant: Towards Accurate Post-Training Quantization of Large Transformer Models via Scale Reparameterization
Zhikai Li, Xuewen Liu, Jing Zhang +1
Large transformer models have demonstrated remarkable success. Post-training quantization (PTQ), which requires only a small dataset for calibration and avoids end-to-end retrainin…