52 citations · 75 across the 21 of their papers we have counts for
24 papers
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…
CacheQuant: Comprehensively Accelerated Diffusion Models
Xuewen Liu, Zhikai Li, Qingyi Gu
Diffusion models have gradually gained prominence in the field of image synthesis, showcasing remarkable generative capabilities. Nevertheless, the slow inference and complex netwo…
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…
TTAQ: Towards Stable Post-training Quantization in Continuous Domain Adaptation
Junrui Xiao, Zhikai Li, Lianwei Yang +2
Post-training quantization (PTQ) reduces excessive hardware cost by quantizing full-precision models into lower bit representations on a tiny calibration set, without retraining. D…
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…
DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation
Xuewen Liu, Zhikai Li, Minhao Jiang +3
Model quantization is a promising method for accelerating and compressing diffusion models. Nevertheless, since post-training quantization (PTQ) fails catastrophically at low-bit c…
K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences
Zhikai Li, Xuewen Liu, Dongrong Joe Fu +4
The rapid advancement of visual generative models necessitates efficient and reliable evaluation methods. Arena platform, which gathers user votes on model comparisons, can rank mo…
MGRQ: Post-Training Quantization For Vision Transformer With Mixed Granularity Reconstruction
Lianwei Yang, Zhikai Li, Junrui Xiao +2
Post-training quantization (PTQ) efficiently compresses vision models, but unfortunately, it accompanies a certain degree of accuracy degradation. Reconstruction methods aim to enh…
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…
LLM Inference Unveiled: Survey and Roofline Model Insights
Zhihang Yuan, Yuzhang Shang, Yang Zhou +11
The field of efficient Large Language Model (LLM) inference is rapidly evolving, presenting a unique blend of opportunities and challenges. Although the field has expanded and is v…
EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Models
Xuewen Liu, Zhikai Li, Junrui Xiao +3
Diffusion models have achieved great success in image generation tasks. However, the lengthy denoising process and complex neural networks hinder their low-latency applications in…
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…
Patch-wise Mixed-Precision Quantization of Vision Transformer
Junrui Xiao, Zhikai Li, Lianwei Yang +1
As emerging hardware begins to support mixed bit-width arithmetic computation, mixed-precision quantization is widely used to reduce the complexity of neural networks. However, Vis…
BinaryViT: Towards Efficient and Accurate Binary Vision Transformers
Junrui Xiao, Zhikai Li, Lianwei Yang +1
Vision Transformers (ViTs) have emerged as the fundamental architecture for most computer vision fields, but the considerable memory and computation costs hinders their application…
RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers
Zhikai Li, Junrui Xiao, Lianwei Yang +1
Post-training quantization (PTQ), which only requires a tiny dataset for calibration without end-to-end retraining, is a light and practical model compression technique. Recently,…
PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers
Zhikai Li, Mengjuan Chen, Junrui Xiao +1
Data-free quantization can potentially address data privacy and security concerns in model compression, and thus has been widely investigated. Recently, PSAQ-ViT designs a relative…
I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference
Zhikai Li, Qingyi Gu
Vision Transformers (ViTs) have achieved state-of-the-art performance on various computer vision applications. However, these models have considerable storage and computational ove…
Patch Similarity Aware Data-Free Quantization for Vision Transformers
Zhikai Li, Liping Ma, Mengjuan Chen +2
Vision transformers have recently gained great success on various computer vision tasks; nevertheless, their high model complexity makes it challenging to deploy on resource-constr…