Tianyu Pang

Orcid: 0000-0003-0639-6176

According to our database¹, Tianyu Pang authored at least 108 papers between 2017 and 2025.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book

In proceedings

Article

PhD thesis

Dataset

Other

Bibliography

2025

Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets.

[BibT_eX]

[DOI]

CoRR, June, 2025

LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning.

[BibT_eX]

[DOI]

CoRR, June, 2025

Fostering Video Reasoning via Next-Event Prediction.

[BibT_eX]

[DOI]

CoRR, May, 2025

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment.

[BibT_eX]

[DOI]

CoRR, May, 2025

Reinforcing General Reasoning without Verifiers.

[BibT_eX]

[DOI]

CoRR, May, 2025

Lifelong Safety Alignment for Language Models.

[BibT_eX]

[DOI]

CoRR, May, 2025

QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design.

[BibT_eX]

[DOI]

CoRR, May, 2025

BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms.

[BibT_eX]

[DOI]

CoRR, May, 2025

Optimizing Anytime Reasoning via Budget Relative Policy Optimization.

[BibT_eX]

[DOI]

CoRR, May, 2025

FlowReasoner: Reinforcing Query-Level Meta-Agents.

[BibT_eX]

[DOI]

CoRR, April, 2025

NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation.

[BibT_eX]

[DOI]

CoRR, April, 2025

Efficient Process Reward Model Training via Active Learning.

[BibT_eX]

[DOI]

CoRR, April, 2025

Understanding R1-Zero-Like Training: A Critical Perspective.

[BibT_eX]

[DOI]

CoRR, March, 2025

SkyLadder: Better and Faster Pretraining via Context Window Scheduling.

[BibT_eX]

[DOI]

CoRR, March, 2025

Error Analyses of Auto-Regressive Video Diffusion Models: A Unified Framework.

[BibT_eX]

[DOI]

CoRR, March, 2025

Unnatural Languages Are Not Bugs but Features for LLMs.

[BibT_eX]

[DOI]

CoRR, March, 2025

LongSpec: Long-Context Speculative Decoding with Efficient Drafting and Verification.

[BibT_eX]

[DOI]

CoRR, February, 2025

Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs.

[BibT_eX]

[DOI]

CoRR, February, 2025

Safety at Scale: A Comprehensive Survey of Large Model Safety.

[BibT_eX]

[DOI]

CoRR, February, 2025

Face3DAdv: Exploiting Robust Adversarial 3D Patches on Physical Face Recognition.

[BibT_eX]

[DOI]

Int. J. Comput. Vis., January, 2025

Improving Your Model Ranking on Chatbot Arena by Vote Rigging.

[BibT_eX]

[DOI]

CoRR, January, 2025

When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2025

From Spikes to Heavy Tails: Unveiling the Spectral Evolution of Neural Networks.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2025

On Memorization in Diffusion Models.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2025

DSAC-T Based Resource Allocation Strategy for Delay Minimization in RIS-Aided MEC Networks.

[BibT_eX]

[DOI]

Proceedings of the 2025 IEEE Wireless Communications and Networking Conference (WCNC), 2025

Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

A Closer Look at Machine Unlearning for Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Scaling up Masked Diffusion Models on Text.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

RegMix: Data Mixture as Regression for Language Model Pre-training.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Improving Long-Text Alignment for Text-to-Image Diffusion Models.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

When Attention Sink Emerges in Language Models: An Empirical View.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Bootstrapping Language Models with DPO Implicit Rewards.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Towards Learning on Vertically Partitioned Data with Distributed Differential Privacy.

[BibT_eX]

[DOI]

Proceedings of the 41st IEEE International Conference on Data Engineering, 2025

Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

2024

Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models.

[BibT_eX]

[DOI]

CoRR, 2024

Real-time Identity Defenses against Malicious Personalization of Diffusion Models.

[BibT_eX]

[DOI]

CoRR, 2024

SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.

[BibT_eX]

[DOI]

CoRR, 2024

Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts.

[BibT_eX]

[DOI]

CoRR, 2024

Denial-of-Service Poisoning Attacks against Large Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

Revisiting Backdoor Attacks against Large Vision-Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

Crafting Heavy-Tails in Weight Matrix Spectrum without Gradient Noise.

[BibT_eX]

[DOI]

CoRR, 2024

Purifying Large Language Models by Ensembling a Small Language Model.

[BibT_eX]

[DOI]

CoRR, 2024

Your Large Language Model is Secretly a Fairness Proponent and You Should Prompt it Like One.

[BibT_eX]

[DOI]

CoRR, 2024

Test-Time Backdoor Attacks on Multimodal Large Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

Weak-to-Strong Jailbreaking on Large Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

Benchmarking Large Multimodal Models against Common Corruptions.

[BibT_eX]

[DOI]

CoRR, 2024

Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Graph Diffusion Policy Optimization.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

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

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Intriguing Properties of Data Attribution on Diffusion Models.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Finetuning Text-to-Image Diffusion Models for Fairness.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Model Balancing Helps Low-data Training and Fine-tuning.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

BAFFLE: A Baseline of Backpropagation-Free Federated Learning.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning.

[BibT_eX]

[DOI]

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

2023

LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition.

[BibT_eX]

[DOI]

CoRR, 2023

Improving Adversarial Robustness of DEQs with Explicit Regulations Along the Neural Dynamics.

[BibT_eX]

[DOI]

CoRR, 2023

CoSDA: Continual Source-Free Domain Adaptation.

[BibT_eX]

[DOI]

CoRR, 2023

A Recipe for Watermarking Diffusion Models.

[BibT_eX]

[DOI]

CoRR, 2023

Does Federated Learning Really Need Backpropagation?

[BibT_eX]

[DOI]

CoRR, 2023

Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

On Evaluating Adversarial Robustness of Large Vision-Language Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

On Calibrating Diffusion Probabilistic Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Efficient Diffusion Policies For Offline Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Gaussian Mixture Solvers for Diffusion Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Bag of Tricks for Training Data Extraction from Language Models.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Improving Adversarial Robustness of Deep Equilibrium Models with Explicit Regulations Along the Neural Dynamics.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Better Diffusion Models Further Improve Adversarial Training.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Nonparametric Generative Modeling with Conditional Sliced-Wasserstein Flows.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Exploring Incompatible Knowledge Transfer in Few-shot Image Generation.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

Query-Efficient Black-Box Adversarial Attacks Guided by a Transfer-Based Prior.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., 2022

O(N<sup>2</sup>) Universal Antisymmetry in Fermionic Neural Networks.

[BibT_eX]

[DOI]

Tianyu Pang

Shuicheng Yan

Min Lin

CoRR, 2022

Controllable Evaluation and Generation of Physical Adversarial Patch on Face Recognition.

[BibT_eX]

[DOI]

CoRR, 2022

A Closer Look at the Adversarial Robustness of Deep Equilibrium Models.

[BibT_eX]

[DOI]

Zonghan Yang

Tianyu Pang

Yang Liu

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Robustness and Accuracy Could Be Reconcilable by (Proper) Definition.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Exploring Memorization in Adversarial Training.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2022, 2022

Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021

Unrestricted Adversarial Attacks on ImageNet Competition.

[BibT_eX]

[DOI]

CoRR, 2021

Model-Agnostic Meta-Attack: Towards Reliable Evaluation of Adversarial Robustness.

[BibT_eX]

[DOI]

CoRR, 2021

Adversarial Attacks on ML Defense Models Competition.

[BibT_eX]

[DOI]

CoRR, 2021

Adversarial Training with Rectified Rejection.

[BibT_eX]

[DOI]

CoRR, 2021

Accumulative Poisoning Attacks on Real-time Data.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Bag of Tricks for Adversarial Training.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Towards Face Encryption by Generating Adversarial Identity Masks.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Black-box Detection of Backdoor Attacks with Limited Information and Data.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

2020

Efficient Learning of Generative Models via Finite-Difference Score Matching.

[BibT_eX]

[DOI]

CoRR, 2020

Towards Privacy Protection by Generating Adversarial Identity Masks.

[BibT_eX]

[DOI]

CoRR, 2020

Boosting Adversarial Training with Hypersphere Embedding.

[BibT_eX]

[DOI]

CoRR, 2020

Boosting Adversarial Training with Hypersphere Embedding.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Efficient Learning of Generative Models via Finite-Difference Score Matching.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Adversarial Distributional Training for Robust Deep Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks.

[BibT_eX]

[DOI]

Tianyu Pang

Kun Xu

Jun Zhu

Proceedings of the 8th International Conference on Learning Representations, 2020

Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

Benchmarking Adversarial Robustness on Image Classification.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019

Benchmarking Adversarial Robustness.

[BibT_eX]

[DOI]

CoRR, 2019

Improving Black-box Adversarial Attacks with a Transfer-based Prior.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Improving Adversarial Robustness via Promoting Ensemble Diversity.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

2018

Adversarial Attacks and Defences Competition.

[BibT_eX]

[DOI]

CoRR, 2018

Detection of DGA Domains Based on Support Vector Machine.

[BibT_eX]

[DOI]

Proceedings of the Third International Conference on Security of Smart Cities, 2018

Towards Robust Detection of Adversarial Examples.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Max-Mahalanobis Linear Discriminant Analysis Networks.

[BibT_eX]

[DOI]

Tianyu Pang

Chao Du

Jun Zhu

Proceedings of the 35th International Conference on Machine Learning, 2018

Defense Against Adversarial Attacks Using High-Level Representation Guided Denoiser.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Boosting Adversarial Attacks With Momentum.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

2017

Discovering Adversarial Examples with Momentum.

[BibT_eX]

[DOI]

CoRR, 2017

Robust Deep Learning via Reverse Cross-Entropy Training and Thresholding Test.

[BibT_eX]

[DOI]

Tianyu Pang

Chao Du

Jun Zhu

CoRR, 2017

Tianyu Pang

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...