23 citations · 143 across the 50 of their papers we have counts for
52 papers
Duplex-MPE: Benchmarking Multi-Party Interaction in Full-Duplex Dialogue
Chengqian Ma, Wenhao Feng, Weixuan Jin +7
Real-time full-duplex speech models can listen while speaking, enabling natural interaction without rigid turn boundaries. Existing benchmarks evaluate turn-taking, interruption ha…
Motion-Aware Caching for Efficient Autoregressive Video Generation
Jing Xu, Yuexiao Ma, Xuzhe Zheng +7
Autoregressive video generation paradigms offer theoretical promise for long video synthesis, yet their practical deployment is hindered by the computational burden of sequential i…
Prototype-Based Test-Time Adaptation of Vision-Language Models
Zhaohong Huang, Yuxin Zhang, Wenjing Liu +2
Test-time adaptation (TTA) has emerged as a promising paradigm for vision-language models (VLMs) to bridge the distribution gap between pre-training and test data. Recent works hav…
HEART: Exploiting Head Heterogeneity in Sparse Attention for Video Diffusion
Xuzhe Zheng, Yuexiao Ma, Jing Xu +3
Sparse attention accelerates video diffusion by allowing each attention head to focus on only a small subset of interactions. Existing methods already construct head-specific spars…
ID-Selection: Importance-Diversity Based Visual Token Selection for Efficient LVLM Inference
Zhaohong Huang, Wenjing Liu, Yuxin Zhang +2
Recent advances have explored visual token pruning to accelerate the inference of large vision-language models (LVLMs). However, existing methods often struggle to balance token im…
Out of the Memory Barrier: A Highly Memory Efficient Training System for LLMs with Million-Token Contexts
Wenhao Li, Daohai Yu, Gen Luo +7
Training Large Language Models (LLMs) on long contexts is severely constrained by prohibitive GPU memory overhead, not training time. The primary culprits are the activations, whos…
CCF: A Context Compression Framework for Efficient Long-Sequence Language Modeling
Wenhao Li, Bangcheng Sun, Weihao Ye +4
Scaling language models to longer contexts is essential for capturing rich dependencies across extended discourse. However, naïve context extension imposes significant computationa…
VISA: Group-wise Visual Token Selection and Aggregation via Graph Summarization for Efficient MLLMs Inference
Pengfei Jiang, Hanjun Li, Linglan Zhao +4
In this study, we introduce a novel method called group-wise \textbf{VI}sual token \textbf{S}election and \textbf{A}ggregation (VISA) to address the issue of inefficient inference…
Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval
Wenhao Li, Yuxin Zhang, Gen Luo +4
Reducing the key-value (KV) cache burden in Large Language Models (LLMs) significantly accelerates inference. Dynamically selecting critical KV caches during decoding helps maintai…
GS-Bias: Global-Spatial Bias Learner for Single-Image Test-Time Adaptation of Vision-Language Models
Zhaohong Huang, Yuxin Zhang, Jingjing Xie +2
Recent advances in test-time adaptation (TTA) for Vision-Language Models (VLMs) have garnered increasing attention, particularly through the use of multiple augmented views of a si…
Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective
Weizhong Huang, Yuxin Zhang, Xiawu Zheng +2
In this paper, we address the challenge of determining the layer-wise sparsity rates of large language models (LLMs) through a theoretical perspective. Specifically, we identify a…
Towards Efficient Automatic Self-Pruning of Large Language Models
Weizhong Huang, Yuxin Zhang, Xiawu Zheng +2
Despite exceptional capabilities, Large Language Models (LLMs) still face deployment challenges due to their enormous size. Post-training structured pruning is a promising solution…
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…
TextDestroyer: A Training- and Annotation-Free Diffusion Method for Destroying Anomal Text from Images
Mengcheng Li, Fei Chao
In this paper, we propose TextDestroyer, the first training- and annotation-free method for scene text destruction using a pre-trained diffusion model. Existing scene text removal…
Move and Act: Enhanced Object Manipulation and Background Integrity for Image Editing
Pengfei Jiang, Mingbao Lin, Fei Chao
Current methods commonly utilize three-branch structures of inversion, reconstruction, and editing, to tackle consistent image editing task. However, these methods lack control ove…
ConCLVD: Controllable Chinese Landscape Video Generation via Diffusion Model
Dingming Liu, Shaowei Li, Ruoyan Zhou +4
Chinese landscape painting is a gem of Chinese cultural and artistic heritage that showcases the splendor of nature through the deep observations and imaginations of its painters.…
Rethinking 3D Dense Caption and Visual Grounding in A Unified Framework through Prompt-based Localization
Yongdong Luo, Haojia Lin, Xiawu Zheng +6
3D Visual Grounding (3DVG) and 3D Dense Captioning (3DDC) are two crucial tasks in various 3D applications, which require both shared and complementary information in localization…
AffineQuant: Affine Transformation Quantization for Large Language Models
Yuexiao Ma, Huixia Li, Xiawu Zheng +6
The significant resource requirements associated with Large-scale Language Models (LLMs) have generated considerable interest in the development of techniques aimed at compressing…
EBFT: Effective and Block-Wise Fine-Tuning for Sparse LLMs
Song Guo, Fan Wu, Lei Zhang +5
Existing methods for fine-tuning sparse LLMs often suffer from resource-intensive requirements and high retraining costs. Additionally, many fine-tuning methods often rely on appro…
Unified-Width Adaptive Dynamic Network for All-In-One Image Restoration
Yimin Xu, Nanxi Gao, Zhongyun Shan +2
In contrast to traditional image restoration methods, all-in-one image restoration techniques are gaining increased attention for their ability to restore images affected by divers…
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…
Boosting the Cross-Architecture Generalization of Dataset Distillation through an Empirical Study
Lirui Zhao, Yuxin Zhang, Fei Chao +1
The poor cross-architecture generalization of dataset distillation greatly weakens its practical significance. This paper attempts to mitigate this issue through an empirical study…
AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration
Lijiang Li, Huixia Li, Xiawu Zheng +7
Diffusion models are emerging expressive generative models, in which a large number of time steps (inference steps) are required for a single image generation. To accelerate such t…
A Unified Framework for 3D Point Cloud Visual Grounding
Haojia Lin, Yongdong Luo, Xiawu Zheng +7
Thanks to its precise spatial referencing, 3D point cloud visual grounding is essential for deep understanding and dynamic interaction in 3D environments, encompassing 3D Referring…