SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals Paper • 2502.01042 • Published Feb 3, 2025 • 1
The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination Paper • 2502.16143 • Published Feb 22, 2025 • 6
Energy-Based Transformers are Scalable Learners and Thinkers Paper • 2507.02092 • Published Jul 2, 2025 • 69
Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers Paper • 2506.23918 • Published Jun 30, 2025 • 89
SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents Paper • 2505.23559 • Published May 29, 2025 • 11
ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind Paper • 2505.22961 • Published May 29, 2025 • 8
Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks Paper • 2501.11733 • Published Jan 20, 2025 • 28
