9 papers
No Prompt, No Leaks: A Robust Generative Steganography Framework via Prompt-Free Diffusion
Jingwen Cai, Fen Xiao, Shuhua Deng +1
Generative image steganography synthesizes stego images directly from secret information to achieve inherent security advantages. Latent Diffusion Models (LDMs) have recently emerg…
Preventing Safety Drift in Large Language Models via Coupled Weight and Activation Constraints
Songping Peng, Zhiheng Zhang, Daojian Zeng +2
Safety alignment in Large Language Models (LLMs) remains highly fragile during fine-tuning, where even benign adaptation can degrade pre-trained refusal behaviors and enable harmfu…
Agents on a Tree: Pathwise Coordination for Multi-Objective Molecular Optimization
Jia Zhang, Tengfei Ma, Tianle Li +3
Multi-objective molecular optimization requires searching vast chemical spaces under conflicting objectives, where early design decisions strongly constrain downstream outcomes. Ex…
Focus-to-Perceive Representation Learning: A Cognition-Inspired Hierarchical Framework for Endoscopic Video Analysis
Yuan Zhang, Sihao Dou, Kai Hu +4
Endoscopic video analysis is essential for early gastrointestinal screening but remains hindered by limited high-quality annotations. While self-supervised video pre-training shows…
Supervised Fine Tuning of Large Language Models for Domain Specific Knowledge Graph Construction:A Case Study on Hunan's Historical Celebrities
Junjie Hao, Chun Wang, Ying Qiao +4
Large language models and knowledge graphs offer strong potential for advancing research on historical culture by supporting the extraction, analysis, and interpretation of cultura…
Distilling Knowledge from Heterogeneous Architectures for Semantic Segmentation
Yanglin Huang, Kai Hu, Yuan Zhang +2
Current knowledge distillation (KD) methods for semantic segmentation focus on guiding the student to imitate the teacher's knowledge within homogeneous architectures. However, the…