Botian Shi

InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models

RRVF: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedback

Investigating Redundancy in Multimodal Large Language Models with Multiple Vision Encoders

GDI-Bench: A Benchmark for General Document Intelligence with Vision and Reasoning Decoupling

IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?

RE-Searcher: Robust Agentic Search via Goal-oriented Planning and Self-reflection

THE-Tree: Can Tracing Historical Evolution Enhance Scientific Verification and Reasoning?

MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks

EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle

OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text

GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training

DocGenome: A Large Benchmark for Multi-Modal Language Models in Real-World Academic Document Understanding

DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving