Min Lin

Bootstrapping Language Models with DPO Implicit Rewards ICLR 2025 Improved Techniques for Optimization-Based Jailbreaking on Large Language Models ICLR 2025 PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization ICML 2025 Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates ICLR 2025 Scaling up Masked Diffusion Models on Text ICLR 2025 Structured Preference Optimization for Vision-Language Long-Horizon Task Planning EMNLP 2025 A Closer Look at Machine Unlearning for Large Language Models ICLR 2025 Improving Your Model Ranking on Chatbot Arena by Vote Rigging ICML 2025 Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts ICCV 2025 ZeroStereo: Zero-shot Stereo Matching from Single Images ICCV 2025 A0: An Affordance-Aware Hierarchical Model for General Robotic Manipulation ICCV 2025 Continual Reinforcement Learning by Planning with Online World Models ICML 2025 RegMix: Data Mixture as Regression for Language Model Pre-training ICLR 2025 When Attention Sink Emerges in Language Models: An Empirical View ICLR 2025 FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation AAAI 2025 Zero Bubble (Almost) Pipeline Parallelism ICLR 2024 Finetuning Text-to-Image Diffusion Models for Fairness ICLR 2024 Intriguing Properties of Data Attribution on Diffusion Models ICLR 2024 Automatic Functional Differentiation in JAX ICLR 2024 Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform ICLR 2024 Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast ICML 2024 Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs NIPS 2024 Graph Diffusion Policy Optimization NIPS 2024 Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses NIPS 2024 Pipeline Parallelism with Controllable Memory NIPS 2024 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies NIPS 2024 Stochastic Taylor Derivative Estimator: Efficient amortization for arbitrary differential operators NIPS 2024 Amortized Eigendecomposition for Neural Networks NIPS 2024 Beyond Memorization: The Challenge of Random Memory Access in Language Models ACL 2024 BAFFLE: A Baseline of Backpropagation-Free Federated Learning ECCV 2024 Sailor: Open Language Models for South-East Asia EMNLP 2024 Locality Sensitive Sparse Encoding for Learning World Models Online ICLR 2024 Better Diffusion Models Further Improve Adversarial Training ICML 2023 Mutual Information Regularized Offline Reinforcement Learning NIPS 2023 On Calibrating Diffusion Probabilistic Models NIPS 2023 On Evaluating Adversarial Robustness of Large Vision-Language Models NIPS 2023 NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF NIPS 2023 Exploring Incompatible Knowledge Transfer in Few-Shot Image Generation CVPR 2023 IHNet: Iterative Hierarchical Network Guided by High-Resolution Estimated Information for Scene Flow Estimation ICCV 2023 D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory ICLR 2023 Nonparametric Generative Modeling with Conditional Sliced-Wasserstein Flows ICML 2023 Bag of Tricks for Training Data Extraction from Language Models ICML 2023 CINO: A Chinese Minority Pre-trained Language Model COLING 2022 Robustness and Accuracy Could Be Reconcilable by (Proper) Definition ICML 2022 EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine NIPS 2022 How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness? NIPS 2021 Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning NIPS 2020 On the Spectral Bias of Neural Networks ICML 2019 Online Continual Learning with Maximal Interfered Retrieval NIPS 2019 Gradient based sample selection for online continual learning NIPS 2019 Global-residual and Local-boundary Refinement Networks for Rectifying Scene Parsing Predictions IJCAI 2017 Correntropy Induced L2 Graph for Robust Subspace Clustering ICCV 2013