1.1k citations · 1.1k across the 23 of their papers we have counts for
21 papers · 1 filter
Towards Purified Multi-Label Test-Time Adaptation of Vision-Language Models
Yiwen Liang, Hui Chen, Yizhe Xiong +7
Test-time adaptation (TTA) has been widely explored in single-label recognition, effectively mitigating distribution shifts, especially when combined with vision-language models. H…
PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning
Fengyuan Sun, Hui Chen, Xinhao Xu +5
While multi-modal large language models (MLLMs) have made significant progress in recent years, the issue of hallucinations remains a major challenge. To mitigate this phenomenon,…
Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual Variations
Yiwen Liang, Hui Chen, Yizhe Xiong +7
Vision-language models (VLMs) exhibit remarkable zero-shot capabilities but struggle with distribution shifts in downstream tasks when labeled data is unavailable, which has motiva…
Neutralizing Token Aggregation via Information Augmentation for Efficient Test-Time Adaptation
Yizhe Xiong, Zihan Zhou, Yiwen Liang +6
Test-Time Adaptation (TTA) has emerged as an effective solution for adapting Vision Transformers (ViT) to distribution shifts without additional training data. However, existing TT…
DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval
Leqi Shen, Guoqiang Gong, Tianxiang Hao +6
The parameter-efficient adaptation of the image-text pretraining model CLIP for video-text retrieval is a prominent area of research. While CLIP is focused on image-level vision-la…
AdaTP: Attention-Debiased Token Pruning for Video Large Language Models
Fengyuan Sun, Leqi Shen, Hui Chen +3
Video Large Language Models (Video LLMs) have achieved remarkable results in video understanding tasks. However, they often suffer from heavy computational overhead due to the larg…
LSNet: See Large, Focus Small
Ao Wang, Hui Chen, Zijia Lin +2
Vision network designs, including Convolutional Neural Networks and Vision Transformers, have significantly advanced the field of computer vision. Yet, their complex computations p…
Cream of the Crop: Harvesting Rich, Scalable and Transferable Multi-Modal Data for Instruction Fine-Tuning
Mengyao Lyu, Yan Li, Huasong Zhong +5
The hypothesis that pretrained large language models (LLMs) necessitate only minimal supervision during the fine-tuning (SFT) stage (Zhou et al., 2024) has been substantiated by re…
YOLOE: Real-Time Seeing Anything
Ao Wang, Lihao Liu, Hui Chen +3
Object detection and segmentation are widely employed in computer vision applications, yet conventional models like YOLO series, while efficient and accurate, are limited by predef…
YOLO-UniOW: Efficient Universal Open-World Object Detection
Lihao Liu, Juexiao Feng, Hui Chen +4
Traditional object detection models are constrained by the limitations of closed-set datasets, detecting only categories encountered during training. While multimodal models have e…
Promptable Anomaly Segmentation with SAM Through Self-Perception Tuning
Hui-Yue Yang, Hui Chen, Ao Wang +7
Segment Anything Model (SAM) has made great progress in anomaly segmentation tasks due to its impressive generalization ability. However, existing methods that directly apply SAM t…
[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs
Ao Wang, Fengyuan Sun, Hui Chen +3
Multimodal Large Language Models (MLLMs) have recently demonstrated strong performance across a wide range of vision-language tasks, garnering significant attention in the computer…
PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation
Ao Wang, Hui Chen, Jiaxin Li +6
Recently, large vision-language models (LVLMs) have rapidly gained popularity for their strong generation and reasoning capabilities given diverse multimodal inputs. However, these…
Context Enhancement with Reconstruction as Sequence for Unified Unsupervised Anomaly Detection
Hui-Yue Yang, Hui Chen, Lihao Liu +5
Unsupervised anomaly detection (AD) aims to train robust detection models using only normal samples, while can generalize well to unseen anomalies. Recent research focuses on a uni…
LLMI3D: MLLM-based 3D Perception from a Single 2D Image
Fan Yang, Sicheng Zhao, Yanhao Zhang +4
Recent advancements in autonomous driving, augmented reality, robotics, and embodied intelligence have necessitated 3D perception algorithms. However, current 3D perception methods…
Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence
Mengyao Lyu, Tianxiang Hao, Xinhao Xu +4
Domain Adaptation (DA) facilitates knowledge transfer from a source domain to a related target domain. This paper investigates a practical DA paradigm, namely Source data-Free Acti…
YOLOv10: Real-Time End-to-End Object Detection
Ao Wang, Hui Chen, Lihao Liu +4
Over the past years, YOLOs have emerged as the predominant paradigm in the field of real-time object detection owing to their effective balance between computational cost and detec…
PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation
Yizhe Xiong, Hui Chen, Tianxiang Hao +6
Recently, the scale of transformers has grown rapidly, which introduces considerable challenges in terms of training overhead and inference efficiency in the scope of task adaptati…
One-Dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications
Mengyao Lyu, Yuhong Yang, Haiwen Hong +6
The prevalent use of commercial and open-source diffusion models (DMs) for text-to-image generation prompts risk mitigation to prevent undesired behaviors. Existing concept erasing…
Towards Efficient Vision-Language Tuning: More Information Density, More Generalizability
Tianxiang Hao, Mengyao Lyu, Hui Chen +4
With the advancement of large pre-trained vision-language models, effectively transferring the knowledge embedded within these foundational models to downstream tasks has become a…
RepViT-SAM: Towards Real-Time Segmenting Anything
Ao Wang, Hui Chen, Zijia Lin +2
Segment Anything Model (SAM) has shown impressive zero-shot transfer performance for various computer vision tasks recently. However, its heavy computation costs remain daunting fo…