6 citations · 24 across the 22 of their papers we have counts for
23 papers
TRAC: Trajectory-aware Reuse and Adaptive Correction for Efficient Autoregressive Video Generation
Jiaxing Song, Weiqi Yan, You Huang +4
Autoregressive (AR) video generation enables scalable long-video synthesis by sequentially generating fixed-length chunks, but incurs substantial computational cost from repeated d…
Lean-SAM2: Target-Anchored Memory and Encoder Acceleration for SAM2
Xudong Ouyang, Wenlun Zhang, Yimin Xu +2
The Segment Anything Model 2 (SAM2) has advanced temporal promptable segmentation, yet its deployment remains hindered by heavy memory cross-attention overhead and redundant full-f…
Neural Reconstruction of LiDAR Point Clouds under Jamming Attacks via Full-Waveform Representation and Simultaneous Laser Sensing
Ryo Yoshida, Takami Sato, Wenlun Zhang +7
LiDAR sensors are critical for autonomous driving perception, yet remain vulnerable to spoofing attacks. Jamming attacks inject high-frequency laser pulses that completely blind Li…
KVSlimmer: Theoretical Insights and Practical Optimizations for Asymmetric KV Merging
Lianjun Liu, Hongli An, Weiqi Yan +4
The growing computational and memory demands of the Key-Value (KV) cache significantly limit the ability of Large Language Models (LLMs). While KV merging has emerged as a promisin…
D4C: Data-Free Quantization for Contrastive Language-Image Pre-training Models
Wenlun Zhang, Yunshan Zhong, Zihao Ding +2
Data-Free Quantization (DFQ) offers a practical solution for model compression without requiring access to real data, making it particularly attractive in privacy-sensitive scenari…
Test-Time Iterative Error Correction for Efficient Diffusion Models
Yunshan Zhong, Weiqi Yan, Yuxin Zhang
With the growing demand for high-quality image generation on resource-constrained devices, efficient diffusion models have received increasing attention. However, such models suffe…
AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization
Wenlun Zhang, Yunshan Zhong, Weiqi Yan +3
The Segment Anything Model (SAM) has revolutionized image and video segmentation with its powerful zero-shot capabilities. However, its massive parameter scale and high computation…
Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers
Yunshan Zhong, Yuyao Zhou, Yuxin Zhang +5
Data-free quantization (DFQ) enables model quantization without accessing real data, addressing concerns regarding data security and privacy. With the growing adoption of Vision Tr…
Towards Accurate Post-Training Quantization of Vision Transformers via Error Reduction
Yunshan Zhong, You Huang, Jiawei Hu +2
Post-training quantization (PTQ) for vision transformers (ViTs) has received increasing attention from both academic and industrial communities due to its minimal data needs and hi…
UIO-LLMs: Unbiased Incremental Optimization for Long-Context LLMs
Wenhao Li, Mingbao Lin, Yunshan Zhong +2
Managing long texts is challenging for large language models (LLMs) due to limited context window sizes. This study introduces UIO-LLMs, an unbiased incremental optimization approa…
Learning Image Demoireing from Unpaired Real Data
Yunshan Zhong, Yuyao Zhou, Yuxin Zhang +2
This paper focuses on addressing the issue of image demoireing. Unlike the large volume of existing studies that rely on learning from paired real data, we attempt to learn a demoi…
I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization
Yunshan Zhong, Jiawei Hu, Mingbao lin +2
Albeit the scalable performance of vision transformers (ViTs), the dense computational costs (training & inference) undermine their position in industrial applications. Post-traini…
Spatial Re-parameterization for N:M Sparsity
Yuxin Zhang, Mingbao Lin, Mingliang Xu +2
This paper presents a Spatial Re-parameterization (SpRe) method for the N:M sparsity. SpRe stems from an observation regarding the restricted variety in spatial sparsity of convolu…
Distribution-Flexible Subset Quantization for Post-Quantizing Super-Resolution Networks
Yunshan Zhong, Mingbao Lin, Jingjing Xie +3
This paper introduces Distribution-Flexible Subset Quantization (DFSQ), a post-training quantization method for super-resolution networks. Our motivation for developing DFSQ is bas…
MBQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization
Yunshan Zhong, Yuyao Zhou, Fei Chao +1
Arbitrary bit-width network quantization has received significant attention due to its high adaptability to various bit-width requirements during runtime. However, in this paper, w…
Bi-directional Masks for Efficient N:M Sparse Training
Yuxin Zhang, Yiting Luo, Mingbao Lin +4
We focus on addressing the dense backward propagation issue for training efficiency of N:M fine-grained sparsity that preserves at most N out of M consecutive weights and achieves…
Shadow Removal by High-Quality Shadow Synthesis
Yunshan Zhong, Lizhou You, Yuxin Zhang +3
Most shadow removal methods rely on the invasion of training images associated with laborious and lavish shadow region annotations, leading to the increasing popularity of shadow i…
Exploiting the Partly Scratch-off Lottery Ticket for Quantization-Aware Training
Yunshan Zhong, Gongrui Nan, Yuxin Zhang +2
Quantization-aware training (QAT) receives extensive popularity as it well retains the performance of quantized networks. In QAT, the contemporary experience is that all quantized…
Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks
Yunshan Zhong, Mingbao Lin, Xunchao Li +5
Light-weight super-resolution (SR) models have received considerable attention for their serviceability in mobile devices. Many efforts employ network quantization to compress SR m…
IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization
Yunshan Zhong, Mingbao Lin, Gongrui Nan +4
Learning to synthesize data has emerged as a promising direction in zero-shot quantization (ZSQ), which represents neural networks by low-bit integer without accessing any of the r…
Fine-grained Data Distribution Alignment for Post-Training Quantization
Yunshan Zhong, Mingbao Lin, Mengzhao Chen +5
While post-training quantization receives popularity mostly due to its evasion in accessing the original complete training dataset, its poor performance also stems from scarce imag…
Re-ID Driven Localization Refinement for Person Search
Chuchu Han, Jiacheng Ye, Yunshan Zhong +4
Person search aims at localizing and identifying a query person from a gallery of uncropped scene images. Different from person re-identification (re-ID), its performance also depe…
Re-Identification Supervised Texture Generation
Jian Wang, Yunshan Zhong, Yachun Li +2
The estimation of 3D human body pose and shape from a single image has been extensively studied in recent years. However, the texture generation problem has not been fully discusse…