Tianyu Pang

P2333's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 20 papers about 22 hours ago

A Recipe for Watermarking Diffusion Models

Paper • 2303.10137 • Published Mar 17, 2023

Adversarial Attacks and Defences Competition

Paper • 1804.00097 • Published Mar 31, 2018

On Evaluating Adversarial Robustness of Large Vision-Language Models

Paper • 2305.16934 • Published May 26, 2023

Intriguing Properties of Data Attribution on Diffusion Models

Paper • 2311.00500 • Published Nov 1, 2023 • 2

Finetuning Text-to-Image Diffusion Models for Fairness

Paper • 2311.07604 • Published Nov 11, 2023

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

Paper • 2402.08567 • Published Feb 13, 2024 • 2

Robustness and Accuracy Could Be Reconcilable by (Proper) Definition

Paper • 2202.10103 • Published Feb 21, 2022

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

Paper • 2402.13669 • Published Feb 21, 2024 • 1

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

Paper • 2406.01288 • Published Jun 3, 2024 • 1

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

Paper • 2406.09136 • Published Jun 13, 2024

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

Paper • 2407.01492 • Published Jul 1, 2024 • 38

Does Federated Learning Really Need Backpropagation?

Paper • 2301.12195 • Published Jan 28, 2023

On Calibrating Diffusion Probabilistic Models

Paper • 2302.10688 • Published Feb 21, 2023 • 1

Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates

Paper • 2410.07137 • Published Oct 9, 2024 • 7

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

Paper • 2410.11817 • Published Oct 15, 2024 • 15

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

Paper • 2411.13476 • Published Nov 20, 2024 • 16

When Attention Sink Emerges in Language Models: An Empirical View

Paper • 2410.10781 • Published Oct 14, 2024

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

Paper • 2502.12982 • Published Feb 18 • 16

Safety at Scale: A Comprehensive Survey of Large Model Safety

Paper • 2502.05206 • Published Feb 2

LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation

Paper • 2410.13846 • Published Oct 17, 2024 • 1