2 citations · 3 across the 17 of their papers we have counts for
17 papers
SafeAtlas-VL: Beyond Binary Multimodal Safety with Large-Scale Data and Guard Models
Zongrui Wang, Xiangyang Zhu, Sicheng Wang +13
Multimodal safety moderation requires distinguishing risks arising from visual content, user intent, and assistant behavior. Existing safeguards, however, are typically trained for…
Media Meets Communication in 6G: Fundamentals, Key Technologies, and Applications
Bingyan Xie, Longyu Zhou, Zihan Chen +9
The rapid advancement of sixth-generation (6G) networks is accelerating the convergence of media intelligence and communication intelligence, driving media communication beyond con…
Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating
Sicheng Wang, Xiangyang Zhu, Han Wang +6
Prior work has shown that fine-tuning large language models on malicious or incorrect outputs in narrow domains can induce broad misalignment and harmful behavior, a phenomenon kno…
Embodied Image Compression
Chunyi Li, Rui Qing, Jianbo Zhang +6
Image Compression for Machines (ICM) has emerged as a pivotal research direction in the field of visual data compression. However, with the rapid evolution of machine intelligence,…
Using GUI Agent for Electronic Design Automation
Chunyi Li, Longfei Li, Zicheng Zhang +4
Graphical User Interface (GUI) agents adopt an end-to-end paradigm that maps a screenshot to an action sequence, thereby automating repetitive tasks in virtual environments. Howeve…
Data Assessment for Embodied Intelligence
Jiahao Xiao, Bowen Yan, Jianbo Zhang +4
In embodied intelligence, datasets play a pivotal role, serving as both a knowledge repository and a conduit for information transfer. The two most critical attributes of a dataset…
MACEval: A Multi-Agent Continual Evaluation Network for Large Models
Zijian Chen, Yuze Sun, Yuan Tian +2
Hundreds of benchmarks dedicated to evaluating large models have been presented over the past few years. However, most of them remain closed-ended and are prone to overfitting due…
ROFI: A Deep Learning-Based Ophthalmic Sign-Preserving and Reversible Patient Face Anonymizer
Yuan Tian, Min Zhou, Yitong Chen +19
Patient face images provide a convenient mean for evaluating eye diseases, while also raising privacy concerns. Here, we introduce ROFI, a deep learning-based privacy protection fr…
MedOmni-45°: A Safety-Performance Benchmark for Reasoning-Oriented LLMs in Medicine
Kaiyuan Ji, Yijin Guo, Zicheng Zhang +4
With the increasing use of large language models (LLMs) in medical decision-support, it is essential to evaluate not only their final answers but also the reliability of their reas…
SafetyFlow: An Agent-Flow System for Automated LLM Safety Benchmarking
Xiangyang Zhu, Yuan Tian, Chunyi Li +3
The rapid proliferation of large language models (LLMs) has intensified the requirement for reliable safety evaluation to uncover model vulnerabilities. To this end, numerous LLM s…
Semantics versus Identity: A Divide-and-Conquer Approach towards Adjustable Medical Image De-Identification
Yuan Tian, Shuo Wang, Rongzhao Zhang +8
Medical imaging has significantly advanced computer-aided diagnosis, yet its re-identification (ReID) risks raise critical privacy concerns, calling for de-identification (DeID) te…
Towards All-in-One Medical Image Re-Identification
Yuan Tian, Kaiyuan Ji, Rongzhao Zhang +4
Medical image re-identification (MedReID) is under-explored so far, despite its critical applications in personalized healthcare and privacy protection. In this paper, we introduce…
VARFVV: View-Adaptive Real-Time Interactive Free-View Video Streaming with Edge Computing
Qiang Hu, Qihan He, Houqiang Zhong +4
Free-view video (FVV) allows users to explore immersive video content from multiple views. However, delivering FVV poses significant challenges due to the uncertainty in view switc…
Medical Manifestation-Aware De-Identification
Yuan Tian, Shuo Wang, Guangtao Zhai
Face de-identification (DeID) has been widely studied for common scenes, but remains under-researched for medical scenes, mostly due to the lack of large-scale patient face dataset…
R-Bench: Are your Large Multimodal Model Robust to Real-world Corruptions?
Chunyi Li, Jianbo Zhang, Zicheng Zhang +8
The outstanding performance of Large Multimodal Models (LMMs) has made them widely applied in vision-related tasks. However, various corruptions in the real world mean that images…
Free-VSC: Free Semantics from Visual Foundation Models for Unsupervised Video Semantic Compression
Yuan Tian, Guo Lu, Guangtao Zhai
Unsupervised video semantic compression (UVSC), i.e., compressing videos to better support various analysis tasks, has recently garnered attention. However, the semantic richness o…
SMC++: Masked Learning of Unsupervised Video Semantic Compression
Yuan Tian, Xiaoyue Ling, Cong Geng +3
Most video compression methods focus on human visual perception, neglecting semantic preservation. This leads to severe semantic loss during the compression, hampering downstream v…