30 citations · 50 across the 17 of their papers we have counts for
20 papers
TacClaw-Infinity: A Large-Scale Vision-Tactile-Language-Action Dataset for Dexterous Manipulation
Fucai Zhu, Xidong Zhang, Yichi Zhang +23
Large-scale robot learning increasingly relies on diverse human demonstrations, yet tactile manipulation data remain difficult to scale, and existing multimodal datasets often lack…
ThinkingGuard: Decoding Implicit Hazards via Step-by-Step Risk Attribution in Multimodal Large Language Models
Ruochen Zhang, Yao Huang, Yitong Sun +5
While Multimodal Large Language Models (MLLMs) are increasingly deployed in safety-critical domains, their reliability is threatened by multimodal implicit risks. Unlike explicit t…
UniNDM: A Unified Noise-driven Detection and Mitigation Framework Against Sexual Content in Text-to-Image Generation
Yao Huang, Yitong Sun, Huanran Chen +8
Despite the impressive generative capabilities of text-to-image diffusion models, they remain vulnerable to implicit sexual prompts, where subtle cues disguised as benign terms or…
MESA: Improving MoE Safety Alignment via Decentralized Expertise
Yitong Sun, Yao Huang, Teng Li +5
Mixture-of-Experts (MoE) architectures scale Large Language Models (LLMs) efficiently, enabling greater capacity with reduced computational cost by dynamically routing inputs to re…
DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios
Yao Huang, Yitong Sun, Yichi Zhang +3
Despite the remarkable advances of Large Language Models (LLMs) across diverse cognitive tasks, the rapid enhancement of these capabilities also introduces emergent deceptive behav…
NDM: A Noise-driven Detection and Mitigation Framework against Implicit Sexual Intentions in Text-to-Image Generation
Yitong Sun, Yao Huang, Ruochen Zhang +4
Despite the impressive generative capabilities of text-to-image (T2I) diffusion models, they remain vulnerable to generating inappropriate content, especially when confronted with…
Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models
Ranjie Duan, Jiexi Liu, Xiaojun Jia +27
Large language models (LLMs) typically deploy safety mechanisms to prevent harmful content generation. Most current approaches focus narrowly on risks posed by malicious actors, of…
DETACH: Cross-domain Learning for Long-Horizon Tasks via Mixture of Disentangled Experts
Yutong Shen, Hangxu Liu, Lei Zhang +4
Long-Horizon (LH) tasks in Human-Scene Interaction (HSI) are complex multi-step tasks that require continuous planning, sequential decision-making, and extended execution across do…
Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigation
Yichi Zhang, Yao Huang, Yifan Wang +10
The trustworthiness of Multimodal Large Language Models (MLLMs) remains an intense concern despite the significant progress in their capabilities. Existing evaluation and mitigatio…
Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space
Yao Huang, Yitong Sun, Shouwei Ruan +3
Large Language Models (LLMs), despite advanced general capabilities, still suffer from numerous safety risks, especially jailbreak attacks that bypass safety protocols. Understandi…
The Path to Reconciling Quality and Safety in Text-to-Image Generation: Dataset, Method, and Evaluation
Shouwei Ruan, Zhenyu Wu, Yao Huang +5
Content safety is a fundamental challenge for text-to-image (T2I) models, yet prevailing methods enforce a debilitating trade-off between safety and generation quality. We argue th…
MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models
Yichi Zhang, Yao Huang, Yitong Sun +10
Despite the superior capabilities of Multimodal Large Language Models (MLLMs) across diverse tasks, they still face significant trustworthiness challenges. Yet, current literature…
Embodied Laser Attack:Leveraging Scene Priors to Achieve Agent-based Robust Non-contact Attacks
Yitong Sun, Yao Huang, Xingxing Wei
As physical adversarial attacks become extensively applied in unearthing the potential risk of security-critical scenarios, especially in dynamic scenarios, their vulnerability to…
Unified Adversarial Patch for Visible-Infrared Cross-modal Attacks in the Physical World
Xingxing Wei, Yao Huang, Yitong Sun +1
Physical adversarial attacks have put a severe threat to DNN-based object detectors. To enhance security, a combination of visible and infrared sensors is deployed in various scena…
Unified Adversarial Patch for Cross-modal Attacks in the Physical World
Xingxing Wei, Yao Huang, Yitong Sun +1
Recently, physical adversarial attacks have been presented to evade DNNs-based object detectors. To ensure the security, many scenarios are simultaneously deployed with visible sen…
Out-of-Distribution Detection with Class Ratio Estimation
Mingtian Zhang, Andi Zhang, Tim Z. Xiao +2
Density-based Out-of-distribution (OOD) detection has recently been shown unreliable for the task of detecting OOD images. Various density ratio based approaches achieve good empir…
Spread Flows for Manifold Modelling
Mingtian Zhang, Yitong Sun, Chen Zhang +1
Flow-based models typically define a latent space with dimensionality identical to the observational space. In many problems, however, the data does not populate the full ambient d…
A Practical Layer-Parallel Training Algorithm for Residual Networks
Qi Sun, Hexin Dong, Zewei Chen +5
Gradient-based algorithms for training ResNets typically require a forward pass of the input data, followed by back-propagating the objective gradient to update parameters, which a…
On the Approximation Properties of Random ReLU Features
Yitong Sun, Anna Gilbert, Ambuj Tewari
We study the approximation properties of random ReLU features through their reproducing kernel Hilbert space (RKHS). We first prove a universality theorem for the RKHS induced by r…
But How Does It Work in Theory? Linear SVM with Random Features
Yitong Sun, Anna Gilbert, Ambuj Tewari
We prove that, under low noise assumptions, the support vector machine with random features (RFSVM) can achieve the learning rate faster than on a training…