23 citations · 52 across the 21 of their papers we have counts for
23 papers
How Reliable Are System-One Decisions in Medicine? A Comparative Study of Jev, Jev-like Models, and LLMs
Yanrui Du, Danyang Zhao, Sendong Zhao +6
Jev has attracted considerable attention for its rapid, generalizable decision-making, yet its medical reliability remains underexplored. To address this gap, our study compares va…
UI-Venus-2 Technical Report
Venus Team, Zhuohan Cai, Haoxing Chen +28
Multimodal GUI agents have emerged as a promising paradigm for digital task automation, yet transitioning from benchmark-oriented models to dependable real-world applications remai…
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification
Yunhao Feng, Ruixiao Lin, Ming Wen +12
LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks. However, existing safety testing targets expert-designed sa…
Constitutional On-Policy Safe Distillation
Ming Wen, Yuxuan Liu, Kun Yang +8
On-policy self-distillation (OPSD) has emerged as an efficient post-training paradigm by using a teacher conditioned on privileged information to provide dense token-level supervis…
Orthogonal Concept Erasure for Diffusion Models
Yuhao Sun, Lingyun Yu, Haoxiang Xu +3
Concept erasure has emerged as a promising approach to mitigate undesired or unsafe content in diffusion models, yet existing methods still face significant limitations. While trai…
UpSafeC: Upcycling for Controllable Safety in Large Language Models
Yuhao Sun, Zhuoer Xu, Shiwen Cui +4
Large Language Models (LLMs) have achieved remarkable progress across a wide range of tasks, but remain vulnerable to safety risks such as harmful content generation and jailbreak…
TraceLLM: Security Diagnosis Through Traces and Smart Contracts in Ethereum
Shuzheng Wang, Yue Huang, Zhuoer Xu +2
Ethereum smart contracts hold tens of billions of USD in DeFi and NFTs, yet comprehensive security analysis remains difficult due to unverified code, proxy-based architectures, and…
Agent Safety Alignment via Reinforcement Learning
Zeyang Sha, Hanling Tian, Zhuoer Xu +3
The emergence of autonomous Large Language Model (LLM) agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents,…
Efficient Transfer Learning for Video-language Foundation Models
Haoxing Chen, Zizheng Huang, Yan Hong +5
Pre-trained vision-language models provide a robust foundation for efficient transfer learning across various downstream tasks. In the field of video action recognition, mainstream…
DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark
Haoxing Chen, Yan Hong, Zizheng Huang +8
Recently, video generation techniques have advanced rapidly. Given the popularity of video content on social media platforms, these models intensify concerns about the spread of fa…
Conditional Prototype Rectification Prompt Learning
Haoxing Chen, Yaohui Li, Zizheng Huang +6
Pre-trained large-scale vision-language models (VLMs) have acquired profound understanding of general visual concepts. Recent advancements in efficient transfer learning (ETL) have…
TroubleLLM: Align to Red Team Expert
Zhuoer Xu, Jianping Zhang, Shiwen Cui +2
Large Language Models (LLMs) become the start-of-the-art solutions for a variety of natural language tasks and are integrated into real-world applications. However, LLMs can be pot…
Segment Anything Model Meets Image Harmonization
Haoxing Chen, Yaohui Li, Zhangxuan Gu +3
Image harmonization is a crucial technique in image composition that aims to seamlessly match the background by adjusting the foreground of composite images. Current methods adopt…
Boosting Audio-visual Zero-shot Learning with Large Language Models
Haoxing Chen, Yaohui Li, Yan Hong +6
Audio-visual zero-shot learning aims to recognize unseen classes based on paired audio-visual sequences. Recent methods mainly focus on learning multi-modal features aligned with c…
Backpropagation Path Search On Adversarial Transferability
Zhuoer Xu, Zhangxuan Gu, Jianping Zhang +3
Deep neural networks are vulnerable to adversarial examples, dictating the imperativeness to test the model's robustness before deployment. Transfer-based attackers craft adversari…
On the Robustness of Latent Diffusion Models
Jianping Zhang, Zhuoer Xu, Shiwen Cui +3
Latent diffusion models achieve state-of-the-art performance on a variety of generative tasks, such as image synthesis and image editing. However, the robustness of latent diffusio…
Mobile User Interface Element Detection Via Adaptively Prompt Tuning
Zhangxuan Gu, Zhuoer Xu, Haoxing Chen +3
Recent object detection approaches rely on pretrained vision-language models for image-text alignment. However, they fail to detect the Mobile User Interface (MUI) element since it…
DiffUTE: Universal Text Editing Diffusion Model
Haoxing Chen, Zhuoer Xu, Zhangxuan Gu +6
Diffusion model based language-guided image editing has achieved great success recently. However, existing state-of-the-art diffusion models struggle with rendering correct text an…
AutoAC: Towards Automated Attribute Completion for Heterogeneous Graph Neural Network
Guanghui Zhu, Zhennan Zhu, Wenjie Wang +3
Many real-world data can be modeled as heterogeneous graphs that contain multiple types of nodes and edges. Meanwhile, due to excellent performance, heterogeneous graph neural netw…
DiffusionInst: Diffusion Model for Instance Segmentation
Zhangxuan Gu, Haoxing Chen, Zhuoer Xu +3
Diffusion frameworks have achieved comparable performance with previous state-of-the-art image generation models. Researchers are curious about its variants in discriminative tasks…
A2: Efficient Automated Attacker for Boosting Adversarial Training
Zhuoer Xu, Guanghui Zhu, Changhua Meng +5
Based on the significant improvement of model robustness by AT (Adversarial Training), various variants have been proposed to further boost the performance. Well-recognized methods…
MT-GBM: A Multi-Task Gradient Boosting Machine with Shared Decision Trees
ZhenZhe Ying, Zhuoer Xu, Zhifeng Li +2
Despite the success of deep learning in computer vision and natural language processing, Gradient Boosted Decision Tree (GBDT) is yet one of the most powerful tools for application…
DIFER: Differentiable Automated Feature Engineering
Guanghui Zhu, Zhuoer Xu, Xu Guo +2
Feature engineering, a crucial step of machine learning, aims to extract useful features from raw data to improve data quality. In recent years, great efforts have been devoted to…