A4-Agent: An Agentic Framework for Zero-Shot Affordance Reasoning

Official Implementation of Paper [DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation]

Official implementation of DA²: Depth Anything in Any Direction

Official implementation of Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model

Official implementation of Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models

STANCE: Motion Coherent Video Generation Via Sparse-to-Dense Anchored Encoding

Official implementation of "Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention"

PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs