Jianwei Yang

LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

Agent Learning via Early Experience

Self-supervised Sparse Vision Concepts for Image Understanding and Reconstruction

Lemon: A Unified and Scalable 3D Multimodal Model for Universal Spatial Understanding

TemporalBench: Evaluating Fine-Grained Temporal Dynamics Understanding for Multimodal Models

GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents

TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies

Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation

Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs

MindJourney: Test-Time Scaling with World Models for Spatial Reasoning

Simplifying DINO via Coding Rate Regularization

Matryoshka Multimodal Models

Latent Action Pretraining from Videos

ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding

OmniParser for Pure Vision Based GUI Agent

TemporalBench: Towards Fine-grained Temporal Understanding for Multimodal Video Models

Evaluating Graphical Perception of Large Multimodal Models