
Multimedia Laboratory @NTUsg, affiliated with S-Lab. Large Multimodal Models, Computer Vision, Image Processing, Computer Graphics, Deep Learning
Singapore
Joined May 2021
- Tweets94
- Following20
- Followers1.8K
- Likes239
MMLab@NTU retweeted
Has GPT-6-Astra Achieved Embodied Intelligence?
Across 12 benchmarks, access to training demonstrations and up to 10× the execution budget push several tasks close to 100% success.
How does this translate to real robots? Watch our demos across 8 robot configurations to see its capabilities and remaining challenges.
Paper: huggingface.co/papers/2610.2…
Project & demos: sensenova.ai/has-gpt-6-astra…
GitHub: github.com/OpenSenseNova/Sen…
MMLab@NTU retweeted
Meet MatAnyone-E: high-quality video matting, much faster. ✂️
Compared with MatAnyone 2 at 4K:
⚡ ~7.4× faster inference
💾 Just 7.6% of the peak GPU memory
✨ Comparable matting quality
Runs at 73 FPS at 1080p and 29 FPS at 4K on a single NVIDIA H200.
Project: shuyun-wang.github.io/projec…
Paper: arxiv.org/abs/2610.35724
Code (coming soon): github.com/Shuyun-Wang/MatAn…
MMLab@NTU retweeted
🎥 A long video. One coherent 3D scene.
Meet HiP3R: piecing together local 3D reconstructions to keep the scene consistent across thousands of frames. Watch the demo and explore the details 👇
Project: kkakkkka.github.io/HiP3R/
Paper: arxiv.org/abs/2610.31635
Code: github.com/HiP3Rs/HiP3R
MMLab@NTU retweeted
What if you could step inside a van Gogh painting?
We used Mundo to imagine new viewpoints from a single painting.
Take a look at this short demo.
Project: mundo-world-model.github.io/
Blog: huggingface.co/blog/Luo-Yiha…
MMLab@NTU retweeted
🌍 Introducing Mundo, led by my student @onelineluo: a customized world model that turns images of a place into an environment for exploration, editing, and simulation.
Explore new viewpoints, change objects and physical properties, or simulate robot navigation and manipulation — all within the captured environment.
The key is an explicit, editable world state: code specifies actions, physics computes their consequences, and a video model renders the outcome using the input images as visual context.
Project: mundo-world-model.github.io/
Blog: huggingface.co/blog/Luo-Yiha…
Code coming soon!
The surprising effectiveness of video diffusion models for hand motion reconstruction
Blog: huggingface.co/blog/Xingang-…
MMLab@NTU retweeted
We’ve open-sourced 🔁 𝗨𝗠𝗠-𝗥𝗲𝗳𝗹𝗲𝗰𝘁𝗶𝗼𝗻 🔁 !
Teaching unified multimodal models to generate, reflect & redraw with 𝘪𝘯𝘵𝘦𝘳𝘭𝘦𝘢𝘷𝘦𝘥 𝘙𝘓.
🚀 GenEval: 0.71 → 0.84, with gains on unseen benchmarks (WISE, T2I-CompBench++, OneIG) too!
huggingface.co/papers/2609.3…
MMLab@NTU retweeted
Most bokeh editors want a sharp photo first. We thought: 𝘄𝗵𝘆 𝗻𝗼𝘁 𝘂𝘀𝗲 𝘁𝗵𝗲 𝗼𝗽𝘁𝗶𝗰𝗮𝗹 𝗰𝗹𝘂𝗲𝘀 𝗮𝗹𝗿𝗲𝗮𝗱𝘆 𝗶𝗻 𝘁𝗵𝗲 𝗯𝗹𝘂𝗿? 🔍
Meet AnyBokeh! Edit bokeh directly in blurred photos. No all-in-focus detour. No test-time calibration. ✨
#NeurIPS2026
MMLab@NTU retweeted
Code as policy, world, or editor: agents can write programs to control robots, represent worlds, and edit visual content.
My student Zunnan @zngmail2 has curated Awesome Code-as-X github.com/kkakkkka/awesome-…, connecting research across these areas through a shared idea: programs as executable, inspectable, and revisable representations. A useful reading list for those exploring this direction. Contributions welcome.
🤖 Made with AI
MMLab@NTU retweeted
Our Puffin-World technical paper is now available.
From one image or text prompt, it generates camera-controlled views with appearance, geometry and physical grounding, then reconstructs them into an explorable 3D world—all in one unified model.
Paper: arxiv.org/abs/2609.04196
Blog: huggingface.co/blog/KangLiao…
Dataset: kangliao929.github.io/projec…
Code: github.com/KangLiao929/Puffi…
Beyond plausible pixels: physically grounded 3D worlds.
Puffin-World is a unified multimodal model that jointly represents appearance, geometry, and physics to perceive, simulate, generate, and reconstruct 3D worlds. Its Omni-Camera representation enables physically grounded viewpoint control, while Puffin-16M scales training across diverse camera configurations and challenging trajectories.
Code, models and data are open.
Blog: huggingface.co/blog/KangLiao…
MMLab@NTU retweeted
We’re hiring a Research Fellow at @MMLabNTU ! The role will explore topics such as neural memory, efficient long-context modelling, and memory-augmented LLM agents. Interested candidates may drop me an email with their CV at ccloy at ntu.edu.sg. Only shortlisted candidates will be contacted.
🤖 Made with AI
MMLab@NTU retweeted
🚀 𝙈𝙖𝙩𝘼𝙣𝙮𝙤𝙣𝙚 2 is accepted to #CVPR2026!
🔥A stronger version of 𝙈𝙖𝙩𝘼𝙣𝙮𝙤𝙣𝙚 with finer details and enhanced robustness🔥
-🏡: pq-yang.github.io/projects/M…
-📜: arxiv.org/abs/2512.11782
-👩🏻💻: github.com/pq-yang/MatAnyone…
MMLab@NTU retweeted
VLANeXt systematically studies what actually matters for VLA performance: policy heads, meta-queries, action chunking, flow matching, temporal history, multi-view, and proprioception, and shows that a simple time-series forecasting perspective improves action prediction.
📄 Paper: arxiv.org/abs/2602.18532
💻 Code: github.com/DravenALG/VLANeXt
If you’re working on VLAs, also check out this curated list of resources:
🔎 github.com/DravenALG/awesome…
MMLab@NTU retweeted
4RC introduces a unified, fully feed-forward framework for monocular 4D reconstruction that encodes an entire video once and then flexibly queries dense 3D geometry and motion for any frame at any timestamp.
By factorizing scene structure into base geometry and time-dependent displacements, it achieves accurate, efficient, and state-of-the-art performance across diverse 4D reconstruction tasks.
Paper: arxiv.org/pdf/2602.10094
Project Page: yihangluo.com/projects/4RC/
RT @ccloy: Congrats to Yuekun @YuekunDai and @ziangcao_ , both from @MMLabNTU , for winning the prestigious Google PhD Fellowship!
Yuekun…
This quoted post is unavailable.
MMLab@NTU retweeted
Introducing 𝐓𝐡𝐢𝐧𝐤𝐢𝐧𝐠 𝐰𝐢𝐭𝐡 𝐂𝐚𝐦𝐞𝐫𝐚📸, a unified multimodal model that integrates camera-centric spatial intelligence to interpret and create scenes from arbitrary viewpoints.
Project Page: kangliao929.github.io/projec…
Code: github.com/KangLiao929/Puffi…
MMLab@NTU retweeted
Thinking with Camera
A Unified Multimodal Model for Camera-Centric Understanding and Generation
MMLab@NTU retweeted
📸Join us at #ICCV2025 for the Mobile Intelligent Photography & Imaging (MIPI) Workshop!
✨Leading keynotes: Profs. @songhan_mit, Michal Irani, Boxin Shi, and @MingHsuanYang - on intelligent photography and efficient GenAI.
🗓Oct 20, 8:50am–12:30pm HST
🔗mipi-challenge.org/
Congratulations to @liuziwei7 of @MMLabNTU , recipient of the Young Scientist Award, recognised for his impactful contributions to computer vision and generative AI. 🎉🎉
🏆 Congrats to #NTUsg Prof Ng Geok Ing on the 🇸🇬 President’s Technology Award 2025. A pioneer in Gallium Nitride (#GaN) – found in fast chargers, EVs, satellites & defence – he built 🇸🇬’s global standing in this field and led the creation of the national GaN centre. 👏 We also congratulate Young Scientist Award recipient Assoc Prof Liu Ziwei, who was recognised for advancing #AI in 3D & 4D vision, as well as digital twins, with impact on healthcare, education and other sectors. #PSTA @NTU_EEE @NTU_ccds
















