AI.info

Peng Ye

Explore Peng Ye on AI.info.

• InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
• FRISM: Fine-Grained Reasoning Injection via Subspace-Level Model Merging for Vision-Language Models
• LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing
• Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
• M-GRPO: Stabilizing Self-Supervised Reinforcement Learning for Large Language Models with Momentum-Anchored Policy Optimization
• ICL-Router: In-Context Learned Model Representations for LLM Routing