Long Ma

This paper introduces a novel supply-chain attack that uses model code backdoors to actively steal sensitive secrets from local LLM fine-tuning datasets, bypassing current privacy defenses.

LARK introduces a novel learnability-grounded approach for selecting reasoning trajectories, significantly improving the efficiency of reasoning distillation by prioritizing trajectories that the student model can learn from.

The paper proposes SafeDIG, a robust safety steering framework that adapts Diffusion Transformers for text-to-image generation by treating safety control as position-aware sparse feature transfer, ensuring reliable safety across different risk domains.