Min Lin

papers

1,874

total citations

papers (26)

Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

ICML 2024arXiv

103

citations

When Attention Sink Emerges in Language Models: An Empirical View

ICLR 2025arXiv

citations

Finetuning Text-to-Image Diffusion Models for Fairness

ICLR 2024arXiv

citations

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

ICLR 2025arXiv

citations

How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?

NEURIPS 2021arXiv

citations

EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine

NEURIPS 2022arXiv

citations

A Closer Look at Machine Unlearning for Large Language Models

ICLR 2025arXiv

citations

A₀ : An Affordance-Aware Hierarchical Model for General Robotic Manipulation

ICCV 2025arXiv

citations

Exploring Incompatible Knowledge Transfer in Few-Shot Image Generation

CVPR 2023arXiv

citations

Zero Bubble (Almost) Pipeline Parallelism

ICLR 2024

citations

Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates

ICLR 2025arXiv

citations

Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts

ICCV 2025arXiv

citations

Locality Sensitive Sparse Encoding for Learning World Models Online

ICLR 2024arXiv

citations

Improving Your Model Ranking on Chatbot Arena by Vote Rigging

ICML 2025arXiv

citations

Mutual Information Regularized Offline Reinforcement Learning

NEURIPS 2023arXiv

citations

NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF

NEURIPS 2023arXiv

citations

Lifelong Safety Alignment for Language Models

NEURIPS 2025arXiv

citations

ZeroStereo: Zero-shot Stereo Matching from Single Images

ICCV 2025arXiv

citations

On Calibrating Diffusion Probabilistic Models

NEURIPS 2023arXiv

citations

FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation

AAAI 2025arXiv

citations

Continual Reinforcement Learning by Planning with Online World Models

ICML 2025arXiv

citations

Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning

NEURIPS 2020

citations

IHNet: Iterative Hierarchical Network Guided by High-Resolution Estimated Information for Scene Flow Estimation

ICCV 2023

citations

Min Lin

papers (26)

Understanding R1-Zero-Like Training: A Critical Perspective

On Evaluating Adversarial Robustness of Large Vision-Language Models

Scaling up Masked Diffusion Models on Text

Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

When Attention Sink Emerges in Language Models: An Empirical View

Finetuning Text-to-Image Diffusion Models for Fairness

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?

EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine

A Closer Look at Machine Unlearning for Large Language Models

A₀ : An Affordance-Aware Hierarchical Model for General Robotic Manipulation

Exploring Incompatible Knowledge Transfer in Few-Shot Image Generation

Zero Bubble (Almost) Pipeline Parallelism

Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates

Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts

Locality Sensitive Sparse Encoding for Learning World Models Online

Improving Your Model Ranking on Chatbot Arena by Vote Rigging

Mutual Information Regularized Offline Reinforcement Learning

NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF

Lifelong Safety Alignment for Language Models

ZeroStereo: Zero-shot Stereo Matching from Single Images

On Calibrating Diffusion Probabilistic Models

FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation

Continual Reinforcement Learning by Planning with Online World Models

Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning

IHNet: Iterative Hierarchical Network Guided by High-Resolution Estimated Information for Scene Flow Estimation

papers (26)

Understanding R1-Zero-Like Training: A Critical Perspective

On Evaluating Adversarial Robustness of Large Vision-Language Models

Scaling up Masked Diffusion Models on Text

Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

When Attention Sink Emerges in Language Models: An Empirical View

Finetuning Text-to-Image Diffusion Models for Fairness

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?

EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine

A Closer Look at Machine Unlearning for Large Language Models

A₀ : An Affordance-Aware Hierarchical Model for General Robotic Manipulation

Exploring Incompatible Knowledge Transfer in Few-Shot Image Generation

Zero Bubble (Almost) Pipeline Parallelism

Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates

Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts

Locality Sensitive Sparse Encoding for Learning World Models Online

Improving Your Model Ranking on Chatbot Arena by Vote Rigging

Mutual Information Regularized Offline Reinforcement Learning

NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF

Lifelong Safety Alignment for Language Models

ZeroStereo: Zero-shot Stereo Matching from Single Images

On Calibrating Diffusion Probabilistic Models

FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation

Continual Reinforcement Learning by Planning with Online World Models

Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning

IHNet: Iterative Hierarchical Network Guided by High-Resolution Estimated Information for Scene Flow Estimation