7 papers
Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Turn Attacks
Siyuan Li, Zehao Liu, Haoyu Li +5
As LLMs become increasingly integrated into complex applications, their vulnerability to adversarial attacks has raised significant concerns. However, existing defenses remain reac…
When Distance Distracts: Representation Distance Bias in BT-Loss for Reward Models
Tong Xie, Andrew Bai, Yuanhao Ban +3
Reward models are central to Large Language Model (LLM) alignment within the framework of RLHF. The standard objective used in reward modeling is the Bradley-Terry (BT) loss, which…
CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks
Siyuan Li, Zehao Liu, Xi Lin +6
As Large Language Models (LLMs) are increasingly deployed in complex applications, their vulnerability to adversarial attacks raises urgent safety concerns, especially those evolvi…
1.x-Distill: Breaking the Diversity, Quality, and Efficiency Barrier in Distribution Matching Distillation
Haoyu Li, Tingyan Wen, Lin Qi +6
Diffusion models produce high-quality text-to-image results, but their iterative denoising is computationally expensive.Distribution Matching Distillation (DMD) emerges as a promis…
Does Few-Shot Learning Help LLM Performance in Code Synthesis?
Derek Xu, Tong Xie, Botao Xia +4
Large language models (LLMs) have made significant strides at code generation through improved model design, training, and chain-of-thought. However, prompt-level optimizations rem…
Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural Networks
Haoyu Li, Shichang Zhang, Longwen Tang +2
Metallic Glasses (MGs) are widely used materials that are stronger than steel while being shapeable as plastic. While understanding the structure-property relationship of MGs remai…