Lichao Sun

papers

1,269

total citations

papers (26)

LLaVA-CoT: Let Vision Language Models Reason Step-by-Step

ICCV 2025arXiv

360

citations

MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark

ICML 2024arXiv

281

citations

Subgraph Federated Learning with Missing Neighbor Generation

NEURIPS 2021arXiv

243

citations

BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs

NEURIPS 2022arXiv

138

citations

MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning

CVPR 2024arXiv

citations

GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding

ICLR 2025arXiv

citations

DataGen: Unified Synthetic Dataset Generation via Large Language Models

ICLR 2025arXiv

citations

In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought

ICML 2024arXiv

citations

Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise

AAAI 2024arXiv

citations

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

NEURIPS 2025arXiv

citations

Scalable Fair Influence Maximization

NEURIPS 2023arXiv

citations

Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World

CVPR 2024arXiv

citations

Improving Interpretation Faithfulness for Vision Transformers

ICML 2024arXiv

citations

BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models

CVPR 2025arXiv

citations

First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training

NEURIPS 2025arXiv

citations

Learning Generalizable Agents via Saliency-guided Features Decorrelation

NEURIPS 2023arXiv

citations

XAttnMark: Learning Robust Audio Watermarking with Cross-Attention

ICML 2025arXiv

citations

Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks

AAAI 2024arXiv

citations

Benchmarking and Analyzing Robust Point Cloud Recognition: Bag of Tricks for Defending Adversarial Examples

ICCV 2023arXiv

citations

TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention

ICCV 2025

citations

Distributional Reward Estimation for Effective Multi-agent Deep Reinforcement Learning

NEURIPS 2022arXiv

citations

ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models

CVPR 2024arXiv

citations

Lichao Sun

papers (26)

LLaVA-CoT: Let Vision Language Models Reason Step-by-Step

MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark

Subgraph Federated Learning with Missing Neighbor Generation

BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs

MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning

GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding

DataGen: Unified Synthetic Dataset Generation via Large Language Models

In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought

Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Scalable Fair Influence Maximization

Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World

Improving Interpretation Faithfulness for Vision Transformers

BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models

First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training

Learning Generalizable Agents via Saliency-guided Features Decorrelation

XAttnMark: Learning Robust Audio Watermarking with Cross-Attention

Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks

Benchmarking and Analyzing Robust Point Cloud Recognition: Bag of Tricks for Defending Adversarial Examples

TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention

Distributional Reward Estimation for Effective Multi-agent Deep Reinforcement Learning

ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models

Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs

Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning

Position: TrustLLM: Trustworthiness in Large Language Models

A Comprehensive Study on Text-attributed Graphs: Benchmarking and Rethinking

papers (26)

LLaVA-CoT: Let Vision Language Models Reason Step-by-Step

MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark

Subgraph Federated Learning with Missing Neighbor Generation

BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs

MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning

GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding

DataGen: Unified Synthetic Dataset Generation via Large Language Models

In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought

Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Scalable Fair Influence Maximization

Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World

Improving Interpretation Faithfulness for Vision Transformers

BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models

First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training

Learning Generalizable Agents via Saliency-guided Features Decorrelation

XAttnMark: Learning Robust Audio Watermarking with Cross-Attention

Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks

Benchmarking and Analyzing Robust Point Cloud Recognition: Bag of Tricks for Defending Adversarial Examples

TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention

Distributional Reward Estimation for Effective Multi-agent Deep Reinforcement Learning

ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models

Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs

Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning

Position: TrustLLM: Trustworthiness in Large Language Models

A Comprehensive Study on Text-attributed Graphs: Benchmarking and Rethinking