Chen Change Loy
@ccloy
Followers
3K
Following
2K
Media
123
Statuses
934
President's Chair Professor @NTUsg Director of @MMLabNTU Computer vision and deep learning
Singapore
Joined November 2010
🚨 Call for Papers – Deadline Approaching!.📸 MIPI Workshop @ ICCV 2025.📅 Oct 20, 2025 | 📍 Honolulu, Hawai‘i. Topics: low-level vision, enhancement, editing, efficient AI, camera systems & more!. Don’t miss your chance to present—submit now:.🔗
0
2
16
RT @kwangmoo_yi: Lan and Luo et al., "STREAM3R: Scalable Sequential 3D Reconstruction with Causal Transformer". Yep, another streaming feed….
0
23
0
RT @HuggingPapers: New from S-Lab, Nanyang Technological University & SenseTime Research: Next Visual Granularity Generation (NVG)!. This n….
0
11
0
RT @TheYihangLuo: STream3R reformulates dense 3D reconstruction into a sequential registration task with causal attention. Just tried 3D r….
0
2
0
Our new preprint: “Next Visual Granularity Generation” - a novel framework for image generation that builds visuals hierarchically, from broad layout to fine detail. Achieves consistent FID improvements (e.g., from 3.30 → 3.03, 2.57 → 2.44, 2.09 → 2.06) compared to VAR in
Introducing "Next Visual Granularity Generation":. An image generation framework with explicit structural decomposition and controllable synthesis. Paper: Huggingface page: PJ page:
0
2
20
RT @camenduru: 👁️ ObjectClear: Complete Object Removal via Object-Effect Attention 🧹 Jupyter Notebook 🥳. Thanks to Jixin Zhao ❤ @Shangchen….
0
23
0
RT @qingke_ai: 北京时间7月8日晚上8点，南洋理工大学MMLab博士生吴鹏浩，将直播分享《GUI-Reflection：让多模态 GUI 智能体获得反思纠错能力的训练框架》。
0
3
0
RT @ai_hakase_: ✨速報✨ 古い動画もAI動画もプロ級に生まれ変わるって知ってました？🎥✨. 「#SeedVR2」を使えば、ボヤけた思い出の動画も、AIで作った動画も、魔法のように超高画質になっちゃうんです！😊. 👇️ このスレッドで解説していきますね！.#AI技….
0
1
0
RT @soumikRakshit96: ✨ CVPR 2025 highlight #2 --- EdgeTAM: On-Device Track Anything Model. EdgeTAM achieves significant speed-ups of 16 fps….
0
54
0
RT @taziku_co: もはや「そこにあった形跡すら残さない」. Object Clearは、ただモノを消すだけではない。床に落ちる影、ガラスへの映り込み、光の反射…それら全てが一緒に処理される。. 昔Photoshopで頑張っていたことをふと思い出す。. https://….
0
5
0
One-step diffusion-based video restoration, SeedVR2, by @Iceclearwjy - you can more clearly observe the differences in the comparisons displayed on the project page
🔥Introducing #SeedVR2, the latest one-step diffusion transformer version of #SeedVR for real-world image and video restoration!. details .- Paper: - Project: - Code (under review):
0
1
7
Congratulations to Ziqi and Ziwei! Grateful for the opportunity to work with so many gifted students at @MMLabNTU. Their passion and creativity continue to inspire us!.
Freshly picked: #NTUsg PhD student Huang Ziqi has been selected as one of 21 global recipients of the prestigious 2025 Apple Scholars in AIML PhD Fellowship — a prestigious programme that supports emerging leaders in AI and machine learning through funding, mentorship, and
3
7
79
RT @BoLi68567011: I’ve worked on evals and once considered turning it into a business. But here’s my honest take o….
github.com
One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks - EvolvingLMMs-Lab/lmms-eval
0
6
0
RT @choiszt: 🚀 Just checked out Aero-1-Audio — a compact 1.5B audio model trained in <24h on 16×H100 from @lmmslab. 🎧 Handles 15+ min audio….
lmms-lab.com
Aero-1-Audio is a 1.5B compact audio model capable of handling a range of audio tasks, including speech recognition, audio understanding, and audio instructions following.
0
8
0
RT @Teslanaut: Oh man. So many amazing tools out there. I really gotta start making a bigger portfolio of what I’ve been learning. Using….
0
53
0