1 citations · 1 across the 19 of their papers we have counts for
20 papers
Sci-MMR: Benchmarking Multi-Step Evidence-Grounded Scientific Reasoning in Multimodal Agents
Jiaqiang Li, Yajie Yang, Zhiheng Xi +15
Autonomous research agents are increasingly expected to search the literature, analyze experimental evidence, and generate scientific hypotheses. These capabilities require multi-s…
ReOrder-OPD:Reliability-Aware Prompt Ordering for On-Policy Distillation
Ximo Zhu, Ruiqi Liu, Rong Wang +8
On-policy distillation (OPD) applies token-level teacher supervision to student-generated trajectories, but this supervision is not always reliable. Existing methods use local conf…
HarmProfile: Characterizing Harmful Distributions in Frontier LLMs
Zhouyuan Ma, Yutao Wu, Hanxun Huang +6
Frontier large language models (LLMs) safety evaluation has largely treated harmful generation as an attack outcome rather than as an object of analysis. Consequently, little is kn…
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…
When Medical Safety Alignment Fails: A Benchmark for Evaluating LLMs on High-Risk Medical Queries
Yige Li, Jun Sun, Wei Zhao +5
Large language models (LLMs) are increasingly used for medical and health-related questions, yet their safety in high-risk medical scenarios remains poorly understood. We introduce…
What Does a Sharing Question Add? Auditing LLM Survey Scores for Misinformation
Zonghuan Xu, Xiang Zheng, Yutao Wu +1
Evaluating misinformation requires distinguishing whether readers believe content from whether they would share it. Asking large language models (LLMs) both questions yields two sc…
Internal Safety Collapse in Frontier Large Language Models
Yutao Wu, Xiao Liu, Yifeng Gao +7
This work identifies a critical failure mode in frontier large language models (LLMs), which we term Internal Safety Collapse (ISC): under certain task conditions, models enter a s…
HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policies
Zhiying Du, Bei Liu, Yaobo Liang +7
Generalist vision--language--action (VLA) policies are typically trained on heterogeneous mixtures of robot demonstrations spanning diverse embodiments, action spaces, and observat…
AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models
Jiayu Li, Yunhan Zhao, Xiang Zheng +4
Vision-Language-Action (VLA) models enable robots to interpret natural-language instructions and perform diverse tasks, yet their integration of perception, language, and control i…
HaluMem: Evaluating Hallucinations in Memory Systems of Agents
Ding Chen, Simin Niu, Kehang Li +6
Memory systems are key components that enable AI systems such as LLMs and AI agents to achieve long-term learning and sustained interaction. However, during memory storage and retr…
ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checking
Yutao Wu, Xiao Liu, Yinghui Li +5
Knowledge poisoning poses a critical threat to Retrieval-Augmented Generation (RAG) systems by injecting adversarial content into knowledge bases, tricking Large Language Models (L…
DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models
Zonghuan Xu, Jiayu Li, Yunhan Zhao +3
Vision-Language-Action (VLA) models map multimodal perception and language instructions to executable robot actions, making them particularly vulnerable to behavioral backdoor mani…
SpineBench: A Clinically Salient, Level-Aware Benchmark Powered by the SpineMed-450k Corpus
Ming Zhao, Wenhui Dong, Yang Zhang +23
Spine disorders affect 619 million people globally and are a leading cause of disability, yet AI-assisted diagnosis remains limited by the lack of level-aware, multimodal datasets.…
Defense-to-Attack: Bypassing Weak Defenses Enables Stronger Jailbreaks in Vision-Language Models
Yunhan Zhao, Xiang Zheng, Xingjun Ma
Despite their superb capabilities, Vision-Language Models (VLMs) have been shown to be vulnerable to jailbreak attacks. While recent jailbreaks have achieved notable progress, thei…
SciML Agents: Write the Solver, Not the Solution
Saarth Gaonkar, Xiang Zheng, Haocheng Xi +5
Recent work in scientific machine learning aims to tackle scientific tasks directly by predicting target values with neural networks (e.g., physics-informed neural networks, neural…
RedTopic: Toward Topic-Diverse Red Teaming of Large Language Models
Jiale Ding, Xiang Zheng, Yutao Wu +5
As large language models (LLMs) are increasingly deployed as black-box components in real-world applications, red teaming has become essential for identifying potential risks. It t…
GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models
Zilong Wang, Xiang Zheng, Xiaosen Wang +3
Text-to-image (T2I) models such as Stable Diffusion have advanced rapidly and are now widely used in content creation. However, these models can be misused to generate harmful cont…
RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming
Xiang Zheng, Xingjun Ma, Wei-Bin Lee +1
Red teaming has proven to be an effective method for identifying and mitigating vulnerabilities in Large Language Models (LLMs). Reinforcement Fine-Tuning (RFT) has emerged as a pr…
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
Xingjun Ma, Yifeng Gao, Yixu Wang +45
The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has reshaped the landscape of Artifici…
BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks
Yunhan Zhao, Xiang Zheng, Lin Luo +3
In this paper, we focus on black-box defense for VLMs against jailbreak attacks. Existing black-box defense methods are either unimodal or bimodal. Unimodal methods enhance either…