← authors · overview

• MoE$^2$-LoRA: When MoE Models Meet MoE-style Low-Rank Adaptation
  2026
• SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents
  2026
• Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
  2026
• Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning
  2026
• VASP Agent: An Agentic Framework for Autonomous First-principles Calculations
  2025
• SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing
  2025
• A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
  2025
• Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning
  2025
• BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset
  2025
• SSRL: Self-Search Reinforcement Learning
  2025
• Intern-S1: A Scientific Multimodal Foundation Model