影响力指数

96.32/100

前 0.2%

全站排名 #123

发表论文86 篇

平均评分5.0

年均产出28.7 篇/年

LEI BAI

Researcher@Shanghai AI Laboratory·中国·OpenReview

研究方向

LLM Multi-Agent · World Models · AI for Science · Atmospheric and Oceanic Sciences · Self-supervised Learning · Video understanding · Spatiotemporal Learning · Correlated time series analysis · Deep Learning

LEI BAI

Squeeze the Soaked Sponge: Efficient Off-policy RFT for Large Language Model

Earth-Agent: Unlocking the Full Landscape of Earth Observation with Agents

Unleashing Scientific Reasoning for Bio-experimental Protocol Generation via Structured Component-based Reward Mechanism

Eigen-Agent: Adaptive Multi-Agent Scientific Reasoning with Monitor-Based RAG

Omni-Weather: A Unified Multimodal Model for Weather Radar Understanding and Generation

EarthSE: A Benchmark Evaluating Earth Scientific Exploration Capability for Large Language Models

SCI-Verifier: Scientific Verifier with Thinking

Transforming Weather Data from Pixel to Latent Space

Mimicking the Physicist's Eye: A VLM-centric Approach for Physics Formula Discovery

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

LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space

InternAgent-MLE: Navigating Fine-Grained Optimization for Coding Agent

DIVA: Discrete Diffusion Vision-Language-Action Models for Parallelized Action Generation

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

OmniEarth-Bench: Probing Cognitive Abilities of MLLMs for Earth's Multi-sphere Observation Data

VeriWeb: Verifiable Long-Chain Web Benchmark for Agentic Information-Seeking

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

Better know nothing than half-know anything: A Precise and Efficient Dataset for Scientific Reasoning in Language Models

Chem-R: Learning to Reason as a Chemist

PhysUniBench: A Multi-Modal Physics Reasoning Benchmark at Undergraduate Level

SpectrumWorld: Artificial Intelligence Foundation for Spectroscopy

LO-SDA: Latent Optimization for Score-based Atmospheric Data Assimilation

ChemBOMAS: Accelerated Bayesian Optimization for Scientific Discovery in Chemistry with LLM-Enhanced Multi-Agent System

SSRL: Self-Search Reinforcement Learning

MODS: Multi-Source Observation Conditional Diffusion Model for Meteorological State Downscaling

Learning Compact Representations of LLM Abilities via Item Response Theory

RewardCode: Training Generalist Code Reward Model via Pairwise Reinforcement Learning

Breaking the Gridlock: Efficient Atmospheric Data Reconstruction and Prediction via Generative 3D Gaussian Splatting

Spatial-Temporal-Spectral Unified Modeling for Remote Sensing Dense Prediction

MCP-R1: Generalized Real-World Task Agent Mastering Dozens of Tools

PhysicsMinions: Winning Gold Medals in the Latest Physics Olympiads with a Coevolutionary Multimodal Multi-Agent System

CompBench: Benchmarking Complex Instruction-guided Image Editing

HiPhO: How Far Are (M)LLMs from Humans in the Latest High School Physics Olympiad Benchmark?

Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement Learning

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

Self-Aware Reinforcement Learning for Improving LLMs with Minimal Data

Diversity for The Win: Towards Building Multi-Agent Systems with Heterogeneous LLMs

DualResearch: Entropy-Gated Dual-Graph Retrieval for Answer Reconstruction

PaX-RAG: Path-augmented and Cross relational Graph Retrieval Augmented Generation via Structural and Semantic Reasoning

Self-Tooling Agent: Dynamically Extending Agent Capabilities through Scientific Tool Synthesis and Invocation

ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering

InternAgent-DR: Advancing deep research with dynamic structured knowledge flow

RoboMonster: Compositional Generalization of Heterogeneous Multi-End Effector Embodied Agents

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning

Nature-Inspired Population-Based Evolution of Large Language Models

MSEarth: A Multimodal Scientific Dataset and Benchmark for Phenomena Uncovering in Earth Science

SenseFlow: A Physics-Informed and Self-Ensembling Iterative Framework for Power Flow Estimation

CTTS: Collective Test-Time Scaling

EWE: An Agentic Framework for Extreme Weather Analysis

Swarm Intelligence Enhanced Reasoning: A Density-Driven Framework for LLM-Based Multi-Agent Optimization

LiveSearchBench: An Automatically Constructed Benchmark for Retrieval and Reasoning over Dynamic Knowledge

Bridging Oceans and Atmosphere: A More Comprehensive Weather Model

Multi-agent Architecture Search via Agentic Supernet

Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policies

LoRA-EnVar: Parameter-Efficient Hybrid Ensemble Variational Assimilation for Weather Forecasting

NUTS: Eddy-Robust Reconstruction of Surface Ocean Nutrients via Two-Scale Modeling

RadarQA: Multi-modal Quality Analysis of Weather Radar Forecasts

scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration

Native-Resolution Image Synthesis

Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement

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

SIFusion: A Unified Fusion Framework for Multi-granularity Arctic Sea Ice Forecasting

Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models

DAWP: A framework for global observation forecasting via Data Assimilation and Weather Prediction in satellite observation space

Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple Preferences

VAE-Var: Variational Autoencoder-Enhanced Variational Methods for Data Assimilation in Meteorology

Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression

Learning Urban Climate Dynamics via Physics-Guided Urban Surface–Atmosphere Interactions

Retro-R1: LLM-based Agentic Retrosynthesis

WeatherGFM: Learning a Weather Generalist Foundation Model via In-context Learning

TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting

WorldSimBench: Towards Video Generation Models as World Simulators

PostCast: Generalizable Postprocessing for Precipitation Nowcasting via Unsupervised Blurriness Modeling

WorldSimBench: Towards Video Generation Models as World Simulators

SenseFlow: A Physics-Informed and Self-Ensembling Iterative Framework for Power Flow Estimation

Diffusion Models Need Visual Priors for Image Generation

How Far are Today's Time-Series Models from Real-world Weather Forecasting Applications?

Transforming Ocean Analysis: Learning 4D ocean field from in-situ observations via uncertainty-aware implicit representations