PaperHub

Chaowei Xiao

~Chaowei_Xiao2

32
论文总数
16.0
年均投稿
5.8
平均评分
接收情况21/32
会议分布
ICLR
23
NeurIPS
5
ICML
2
COLM
2

发表论文 (32 篇)

202519 篇

4.9
4

MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines

ICML 2025Poster
4.3
4

MetaAgent: Automatically Building Multi-Agent System based on Finite State Machine

ICLR 2025Rejected
5.5
4

Sample-specific Noise Injection for Diffusion-based Adversarial Purification

ICLR 2025Rejected
6.1
4

Sample-specific Noise Injection for Diffusion-based Adversarial Purification

ICML 2025Poster
6.8
4

Robust Representation Consistency Model via Contrastive Denoising

ICLR 2025Poster
5.5
4

SafeVision: Efficient Image Guardrail with Robust Policy Adherence and Explainability

ICLR 2025Rejected
4.3
4

AutoHijacker: Automatic Indirect Prompt Injection Against Black-box LLM Agents

ICLR 2025Rejected
5.8
4

LeanAgent: Lifelong Learning for Formal Theorem Proving

ICLR 2025Poster
6.3
3

JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model

COLM 2025Poster
7.0
4

T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching

ICLR 2025Poster
6.6
5

EIA: ENVIRONMENTAL INJECTION ATTACK ON GENERALIST WEB AGENTS FOR PRIVACY LEAKAGE

ICLR 2025Poster
5.8
5

Can Watermarks be Used to Detect LLM IP Infringement For Free?

ICLR 2025Poster
6.4
4

DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents

NeurIPS 2025Poster
6.0
4

DataGen: Unified Synthetic Dataset Generation via Large Language Models

ICLR 2025Poster
7.2
6

AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs

ICLR 2025Spotlight
4.4
5

Can Editing LLMs Inject Harm?

ICLR 2025Rejected
5.3
4

Prompt Injection Benchmark for Foundation Model Integrated Systems

ICLR 2025Rejected
5.4
5

Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset

ICLR 2025Poster
5.2
5

MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding

ICLR 2025Poster

202413 篇

7.3
4

HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection

NeurIPS 2024Spotlight
-

Poisoning-based Backdoor Attack against Vision-Language Model

ICLR 2024withdrawn
5.5
4

CSI: Enhancing the Robustness of 3D Point Cloud Recognition against Corruption

ICLR 2024Rejected
5.2
5

AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases

NeurIPS 2024Poster
5.3
4

Understanding Multimodal Instruction Format for In-context Learning

ICLR 2024Rejected
7.0
4

AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

ICLR 2024Poster
6.8
4

JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks

COLM 2024Poster
5.8
4

Leveraging Hierarchical Feature Sharing for Efficient Dataset Condensation

ICLR 2024Rejected
5.5
4

T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching

ICLR 2024Rejected
6.7
3

CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception

ICLR 2024Poster
6.0
3

Conversational Drug Editing Using Retrieval and Domain Feedback

ICLR 2024Poster
5.0
3

Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness

NeurIPS 2024Poster
6.3
4

BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment

NeurIPS 2024Poster
合作者 (20)