Jun Luo

4 papers Nanyang Technological University

• Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs
• Co-Reinforcement Learning for Unified Multimodal Understanding and Generation
• LOPT: Learning Optimal Pigovian Tax in Sequential Social Dilemmas
• Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents