45 citations · 69 across the 29 of their papers we have counts for
29 papers
Confidence-Aware Alignment Makes Reasoning LLMs More Reliable
Kejia Chen, Jiawen Zhang, Yihong Wu +5
Large reasoning models often reach correct answers through flawed intermediate steps, creating a gap between final accuracy and reasoning reliability. Existing alignment strategies…
Token-Level Inference-Time Alignment for Vision-Language Models
Kejia Chen, Jiawen Zhang, Jiacong Hu +4
Vision-Language Models (VLMs) have become essential backbones of modern multimodal intelligence, yet their outputs remain prone to hallucination-plausible text misaligned with visu…
RS3DBench: A Comprehensive Benchmark for 3D Spatial Perception in Remote Sensing
Jiayu Wang, Ruizhi Wang, Jie Song +4
In this paper, we introduce a novel benchmark designed to propel the advancement of general-purpose, large-scale 3D vision models for remote sensing imagery. While several datasets…
Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models
Kejia Chen, Jiawen Zhang, Jiacong Hu +4
Quantized large language models (LLMs) have gained increasing attention and significance for enabling deployment in resource-constrained environments. However, emerging studies on…
SHAPE : Self-Improved Visual Preference Alignment by Iteratively Generating Holistic Winner
Kejia Chen, Jiawen Zhang, Jiacong Hu +4
Large Visual Language Models (LVLMs) increasingly rely on preference alignment to ensure reliability, which steers the model behavior via preference fine-tuning on preference data…
SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models
Jiawen Zhang, Kejia Chen, Zunlei Feng +4
With the growing popularity of LLMs among the general public users, privacy-preserving and adversarial robustness have become two pressing demands for LLM-based services, which hav…
Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense
Jiawen Zhang, Kejia Chen, Lipeng He +7
Large Language Models (LLMs) have showcased remarkable capabilities across various domains. Accompanying the evolving capabilities and expanding deployment scenarios of LLMs, their…
SEW: Self-calibration Enhanced Whole Slide Pathology Image Analysis
Haoming Luo, Xiaotian Yu, Shengxuming Zhang +8
Pathology images are considered the ``gold standard" for cancer diagnosis and treatment, with gigapixel images providing extensive tissue and cellular information. Existing methods…
Efficient and Comprehensive Feature Extraction in Large Vision-Language Model for Pathology Analysis
Shengxuming Zhang, Weihan Li, Tianhong Gao +6
Pathological diagnosis is vital for determining disease characteristics, guiding treatment, and assessing prognosis, relying heavily on detailed, multi-scale analysis of high-resol…
Deep Feature Response Discriminative Calibration
Wenxiang Xu, Tian Qiu, Linyun Zhou +3
Deep neural networks (DNNs) have numerous applications across various domains. Several optimization techniques, such as ResNet and SENet, have been proposed to improve model accura…
Progressive Feature Self-reinforcement for Weakly Supervised Semantic Segmentation
Jingxuan He, Lechao Cheng, Chaowei Fang +3
Compared to conventional semantic segmentation with pixel-level supervision, Weakly Supervised Semantic Segmentation (WSSS) with image-level labels poses the challenge that it alwa…
An Integrated Visual Analytics System for Studying Clinical Carotid Artery Plaques
Chaoqing Xu, Zhentao Zheng, Yiting Fu +5
Carotid artery plaques can cause arterial vascular diseases such as stroke and myocardial infarction, posing a severe threat to human life. However, the current clinical examinatio…
Graph Neural Networks-based Hybrid Framework For Predicting Particle Crushing Strength
Tongya Zheng, Tianli Zhang, Qingzheng Guan +4
Graph Neural Networks have emerged as an effective machine learning tool for multi-disciplinary tasks such as pharmaceutical molecule classification and chemical reaction predictio…
A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision
Zhonghan Zhao, Wenhao Chai, Shengyu Hao +6
Deep learning has the potential to revolutionize sports performance, with applications ranging from perception and comprehension to decision. This paper presents a comprehensive su…
Spatiotemporal-Augmented Graph Neural Networks for Human Mobility Simulation
Yu Wang, Tongya Zheng, Shunyu Liu +4
Human mobility patterns have shown significant applications in policy-decision scenarios and economic behavior researches. The human mobility simulation task aims to generate human…
ViT-Calibrator: Decision Stream Calibration for Vision Transformer
Lin Chen, Zhijie Jia, Tian Qiu +4
A surge of interest has emerged in utilizing Transformers in diverse vision tasks owing to its formidable performance. However, existing approaches primarily focus on optimizing in…
Non-stationary Delayed Online Convex Optimization: From Full-information to Bandit Setting
Yuanyu Wan, Chang Yao, Yitao Ma +2
Although online convex optimization (OCO) under arbitrary delays has received increasing attention recently, previous studies focus on stationary environments with the goal of mini…
Life Regression based Patch Slimming for Vision Transformers
Jiawei Chen, Lin Chen, Jiang Yang +4
Vision transformers have achieved remarkable success in computer vision tasks by using multi-head self-attention modules to capture long-range dependencies within images. However,…
Propheter: Prophetic Teacher Guided Long-Tailed Distribution Learning
Wenxiang Xu, Yongcheng Jing, Linyun Zhou +4
The problem of deep long-tailed learning, a prevalent challenge in the realm of generic visual recognition, persists in a multitude of real-world applications. To tackle the heavil…
Team DETR: Guide Queries as a Professional Team in Detection Transformers
Tian Qiu, Linyun Zhou, Wenxiang Xu +3
Recent proposed DETR variants have made tremendous progress in various scenarios due to their streamlined processes and remarkable performance. However, the learned queries usually…
Model Doctor for Diagnosing and Treating Segmentation Error
Zhijie Jia, Lin Chen, Kaiwen Hu +3
Despite the remarkable progress in semantic segmentation tasks with the advancement of deep neural networks, existing U-shaped hierarchical typical segmentation networks still suff…
DIVOTrack: A Novel Dataset and Baseline Method for Cross-View Multi-Object Tracking in DIVerse Open Scenes
Shenghao Hao, Peiyuan Liu, Yibing Zhan +5
Cross-view multi-object tracking aims to link objects between frames and camera views with substantial overlaps. Although cross-view multi-object tracking has received increased at…
SASFormer: Transformers for Sparsely Annotated Semantic Segmentation
Hui Su, Yue Ye, Wei Hua +2
Semantic segmentation based on sparse annotation has advanced in recent years. It labels only part of each object in the image, leaving the remainder unlabeled. Most of the existin…
Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation
Siqi Fan, Fenghua Zhu, Zunlei Feng +3
Pseudo supervision is regarded as the core idea in semi-supervised learning for semantic segmentation, and there is always a tradeoff between utilizing only the high-quality pseudo…