Lei Bai

Sci-CoE: Co-evolving Scientific Reasoning LLMs via Geometric Consensus with Sparse Supervision

arXiv 2026

Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development

arXiv 2026

SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents

arXiv 2026

Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale

arXiv 2026

StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction

arXiv 2026

P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads

arXiv 2026

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

arXiv 2025

A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers

arXiv 2025

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

arXiv 2025

NovelSeek: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification

arXiv 2025

Multi-agent Architecture Search via Agentic Supernet

arXiv 2025

SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing

arXiv 2025

MASLab: A Unified and Comprehensive Codebase for LLM-based Multi-Agent Systems

arXiv 2025

The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants

arXiv 2025

Native-Resolution Image Synthesis

arXiv 2025

VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning

arXiv 2025

OmniCaptioner: One Captioner to Rule Them All

arXiv 2025

Dolphin: Closed-loop Open-ended Auto-research through Thinking, Practice, and Feedback

arXiv 2025

ChemMLLM: Chemical Multimodal Large Language Model

arXiv 2025

MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs

arXiv 2025

CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics

arXiv 2025

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

arXiv 2025

Transition Models: Rethinking the Generative Learning Objective

arXiv 2025

Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation

arXiv 2025

From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery

arXiv 2025

CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards

arXiv 2025

BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset

arXiv 2025

InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis

arXiv 2025

SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines

arXiv 2025

Chem-R: Learning to Reason as a Chemist

arXiv 2025

VeriGUI: Verifiable Long-Chain GUI Dataset

arXiv 2025

SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence

arXiv 2025

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

arXiv 2025

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

arXiv 2025

SSRL: Self-Search Reinforcement Learning

arXiv 2025

Omni-Weather: Unified Multimodal Foundation Model for Weather Generation and Understanding

arXiv 2025

P1: Mastering Physics Olympiads with Reinforcement Learning

arXiv 2025

Nature-Inspired Population-Based Evolution of Large Language Models

arXiv 2025

PredBench: Benchmarking Spatio-Temporal Prediction across Diverse Disciplines

arXiv 2024

ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems

CVPR 2025 1

On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection

arXiv 2024

Q-Refine: A Perceptual Quality Refiner for AI-Generated Image

arXiv 2024

Online Test-Time Adaptation of Spatial-Temporal Traffic Flow Forecasting

arXiv 2024