AI.info

Jun Xu

Explore Jun Xu on AI.info.

• GeoRA: Geometry-Aware Low-Rank Adaptation for RLVR
• Silence the Judge: Reinforcement Learning with Self-Verifier via Latent Geometric Clustering
• Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction
• VoiceAgentEval: A Dual-Dimensional Benchmark for Expert-Level Intelligent Voice-Agent Evaluation of Xbench's Professional-Aligned Series