Linjie Li

Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations

AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning

OR-PRM: A Process Reward Model for Algorithmic Problem in Operations Research

EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing

3D-CoS: A New 3D Reconstruction Paradigm Based on VLM Code Synthesis

STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models

ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning

FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow

TextAtlas5M: A Large-Scale Dataset for Long and Structured Text Image Generation

InfoAgent: Advancing Autonomous Information‑Seeking Agents

V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models

Unary Feedback as Observation: Incentivizing Self-Reflection in Large Language Models via Multi-Turn RL

Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT

Shanks: Simultaneous Hearing and Thinking for Spoken Language Models

Are Unified Vision-Language Models Necessary: Generalization Across Understanding and Generation

Where do Reasoning Models Make a Difference? Follow the Reasoning Leader for Efficient Decoding

Computer-Use Agents as Judges for Automatic GUI Design

VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation

The Agent's Marathon: Probing the Limits of Endurance in Long-Horizon Tasks

Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark

MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models

SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation

VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents

SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement

ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs

EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing

Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning

GenXD: Generating Any 3D and 4D Scenes

CertainlyUncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness

MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos

OmniContrast: Vision-Language-Interleaved Contrast from Pixels All at once

Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback