Get started
Author

Lei Bai

X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs
2025 · Ye, Rui, Liu, Xiangrui, et al. · arXiv (Cornell University) · 4
PDF
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
2026 · Zou, Yicheng, Zhu, Dongsheng, et al. · arXiv (Cornell University) · 1
PDF
VASP Agent: An Agentic Framework for Autonomous First-principles Calculations
2025 · Xia, Zeyu, Ma, Jinzhe, et al. · arXiv (Cornell University) · 1
PDF
LabOPBench: A Multimodal Benchmark for Evidence-Grounded Laboratory Decision Making
2026 · Li, Jingyuan, Liu, Yujie, et al. · arXiv (Cornell University)
PDF
Sci-MMR: Benchmarking Multi-Step Evidence-Grounded Scientific Reasoning in Multimodal Agents
2026 · Li, Jiaqiang, Yang, Yajie, et al. · arXiv (Cornell University)
PDF
Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement
2026 · Yan, Haoyang, Su, Min-le, et al. · arXiv (Cornell University)
PDF
Learning from Hard Prompts: Difficulty-aware Advantage Amplification in Dynamic Sampling
2026 · Gan, Siyuan, Li, Yuhan, et al. · arXiv (Cornell University)
PDF
SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning
2026 · He, Haonan, Lei, Haodi, et al. · arXiv (Cornell University)
PDF
Intern-S2-Preview: Scientific Agentic Foundation Model
2026 · Bai, Lei, Cao, Jiaqi, et al. · arXiv (Cornell University)
PDF
AgentPanel: Toward a New Paradigm for Human--AI Collaboration in Exploring Scientific Questions
2026 · Cui, Zhiyao, Wang, Qianyi, et al. · arXiv (Cornell University)
PDF
SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation
2026 · Tan, Zelin, Zhang, Yiqun, et al. · arXiv (Cornell University)
PDF
AutoSupervision: Closing the Feedback Loop in Scientific Workflows with Grounded Revision Verification
2026 · Li, Haobo, Jung, Eunseo, et al. · arXiv (Cornell University)
PDF
MoE$^2$-LoRA: When MoE Models Meet MoE-style Low-Rank Adaptation
2026 · Yang, Qingyu, He, Haonan, et al. · arXiv (Cornell University)
PDF
DeepSafe-SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring
2026 · Li, Chunxiao, Xiong, Yuan, et al. · arXiv (Cornell University)
PDF
SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery
2026 · SciForge Team, Gao, Zhangyang, et al. · arXiv (Cornell University)
PDF
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
2026 · Bai, Lei, Cao, Zongsheng, et al. · arXiv (Cornell University)
PDF
LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories
2026 · Ren, Baochang, Liu, Xinjie, et al. · arXiv (Cornell University)
PDF
MSEarth: A Multimodal Benchmark for Earth Science Phenomenon Discovery with MLLMs
2026 · Association for Computational Linguistics 2026, Bai, Lei, et al. · Underline Science Inc.
A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions
2026 · Association for Computational Linguistics 2026, Bai, Lei, et al. · Underline Science Inc.
FlowSearch: Advancing Deep Research with Dynamic Structured Knowledge Flow
2026 · Association for Computational Linguistics 2026, Bai, Lei, et al. · Underline Science Inc.
A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement
2026 · Association for Computational Linguistics 2026, Bai, Lei, et al. · Underline Science Inc.
Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning
2026 · Association for Computational Linguistics 2026, Bai, Lei, et al. · Underline Science Inc.
Nature-Inspired Population-Based Evolution of Large Language Models
2026 · Association for Computational Linguistics 2026, Bai, Lei, et al. · Underline Science Inc.
Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning
2026 · Association for Computational Linguistics 2026, Bai, Lei, et al. · Underline Science Inc.
MTRouter: Cost-Aware Multi-Turn LLM Routing with History–Model Joint Embeddings
2026 · Association for Computational Linguistics 2026, Bai, Lei, et al. · Underline Science Inc.
Works count: 54
Citation count: 6
H-index: 1
I10-index:
Year
Topic
Type