Tianyu Pang

Error Analyses of Auto-Regressive Video Diffusion Models JMLR 2026 LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification ACL 2026 Suspicious Alignment of SGD:A Fine-Grained Step Size Condition Analysis ALT 2026 Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets ACL 2026 A Closer Look at Machine Unlearning for Large Language Models ICLR 2025 BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms ICML 2025 Bootstrapping Language Models with DPO Implicit Rewards ICLR 2025 Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates ICLR 2025 Improved Techniques for Optimization-Based Jailbreaking on Large Language Models ICLR 2025 Improving Long-Text Alignment for Text-to-Image Diffusion Models ICLR 2025 Improving Your Model Ranking on Chatbot Arena by Vote Rigging ICML 2025 LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning ICML 2025 Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts ICCV 2025 Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models ICML 2025 RegMix: Data Mixture as Regression for Language Model Pre-training ICLR 2025 Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift CVPR 2025 Scaling up Masked Diffusion Models on Text ICLR 2025 Unnatural Languages Are Not Bugs but Features for LLMs ICML 2025 Weak-to-Strong Jailbreaking on Large Language Models ICML 2025 When Attention Sink Emerges in Language Models: An Empirical View ICLR 2025 Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast ICML 2024 BAFFLE: A Baseline of Backpropagation-Free Federated Learning ECCV 2024 Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs NeurIPS 2024 Finetuning Text-to-Image Diffusion Models for Fairness ICLR 2024 Graph Diffusion Policy Optimization NeurIPS 2024 Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses NeurIPS 2024 Intriguing Properties of Data Attribution on Diffusion Models ICLR 2024 Model Balancing Helps Low-data Training and Fine-tuning EMNLP 2024 Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning ACL 2024 Bag of Tricks for Training Data Extraction from Language Models ICML 2023 Better Diffusion Models Further Improve Adversarial Training ICML 2023 Efficient Diffusion Policies For Offline Reinforcement Learning NeurIPS 2023 Exploring Incompatible Knowledge Transfer in Few-Shot Image Generation CVPR 2023 Gaussian Mixture Solvers for Diffusion Models NeurIPS 2023 Improving Adversarial Robustness of Deep Equilibrium Models with Explicit Regulations Along the Neural Dynamics ICML 2023 Nonparametric Generative Modeling with Conditional Sliced-Wasserstein Flows ICML 2023 On Calibrating Diffusion Probabilistic Models NeurIPS 2023 On Evaluating Adversarial Robustness of Large Vision-Language Models NeurIPS 2023 Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training NeurIPS 2023 A Closer Look at the Adversarial Robustness of Deep Equilibrium Models NeurIPS 2022 Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks ECCV 2022 Exploring Memorization in Adversarial Training ICLR 2022 Robustness and Accuracy Could Be Reconcilable by (Proper) Definition ICML 2022 Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart CVPR 2022 Accumulative Poisoning Attacks on Real-time Data NeurIPS 2021 Bag of Tricks for Adversarial Training ICLR 2021 Black-Box Detection of Backdoor Attacks With Limited Information and Data ICCV 2021 Towards Face Encryption by Generating Adversarial Identity Masks ICCV 2021 Adversarial Distributional Training for Robust Deep Learning NeurIPS 2020 Benchmarking Adversarial Robustness on Image Classification CVPR 2020 Boosting Adversarial Training with Hypersphere Embedding NeurIPS 2020 Efficient Learning of Generative Models via Finite-Difference Score Matching NeurIPS 2020 Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness ICLR 2020 Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks CVPR 2019 Improving Adversarial Robustness via Promoting Ensemble Diversity ICML 2019 Improving Black-box Adversarial Attacks with a Transfer-based Prior NeurIPS 2019 Boosting Adversarial Attacks With Momentum CVPR 2018 Defense Against Adversarial Attacks Using High-Level Representation Guided Denoiser CVPR 2018 Max-Mahalanobis Linear Discriminant Analysis Networks ICML 2018 Towards Robust Detection of Adversarial Examples NeurIPS 2018