MMLab@NTU

university

https://www.mmlab-ntu.com/

Activity Feed Request to join this org

AI & ML interests

Computer Vision and Deep Learning

Recent Activity

DravenALG updated a collection about 21 hours ago

DravenALG authored a paper about 21 hours ago

Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States

Ziqi updated a collection 1 day ago

View all activity

Papers

Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence

Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion

View all Papers

mmlab-ntu 's papers 13

Submitted by

leoli

Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence

mmlab-ntu

Submitted by

weichenfan

Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion

mmlab-ntu

Submitted by

Haozhe Xie

MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction

mmlab-ntu

Submitted by

Haozhe Xie

Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer

mmlab-ntu

Submitted by

Yuhao Dong

Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models

mmlab-ntu

2

Submitted by

Yukang Cao

Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation

mmlab-ntu

Submitted by

Yukang Cao

HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions

mmlab-ntu

Submitted by

Xiao-Ming Wu

VLANeXt: Recipes for Building Strong VLA Models

mmlab-ntu

Submitted by

Yihang Luo

4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere

mmlab-ntu

Submitted by

Yuhao Dong

Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisition

mmlab-ntu

Submitted by

Haozhe Xie

DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation

mmlab-ntu

Submitted by

Kang Liao

Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation

mmlab-ntu