Min Lin

13

Papers

465

Total Citations

Papers (13)

Scaling up Masked Diffusion Models on Text

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

A Closer Look at Machine Unlearning for Large Language Models

Zero Bubble (Almost) Pipeline Parallelism

Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates

Locality Sensitive Sparse Encoding for Learning World Models Online

Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts

FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation

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

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

ZeroStereo: Zero-shot Stereo Matching from Single Images