Rui Pan

4 papers Beijing University of Posts and Telecommunications

• ASGO: Adaptive Structured Gradient Optimization
• NegoCollab: A Common Representation Negotiation Approach for Heterogeneous Collaborative Perception
• Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
• SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning