🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Wow, it seems that we need to be well prepared for its registration as well Jiwan Kim Hyunsung Cho

To give a keynote on "Pursuing the Nature of Intelligence" on Friday the 25th at the upcoming ICLR 2025: iclr.cc/virtual/2025/i… See many of you in Singapore in a few days. This is a BIG topic, and I will try my best and see if I can pull it off.

Great experience at the opening remarks at CVM and HKUST AI Film Festival by Maneesh Agrawala

🚀 Heading to #ICLR2025 Singapore 🇸🇬 to present IC-Light: Scaling In-the-Wild Training for Diffusion-Based Illumination Control! 🌟 Paper: openreview.net/pdf?id=u1cQYxR… Code: github.com/lllyasviel/IC-… Demo: huggingface.co/spaces/lllyasv…

The calm before the storm #ICLR2025 🔥🔥🔥

It is too HOT popular #ICLR2025 Spent one hour to get my badge

Time for ICLR 2025! ‘Diffusion’ decreased to 290 ‘LLM’ increased to 325 Only 2 ‘NeRF’ papers! And 11 ‘Dream’ papers, encouraging trend 😅

Loving the poster session energy! #ICLR2025

Yang Song OpenAI presents simplifying, stabilizing and scaling continuous time consistency models #ICLR2025

I am at #ICLR2025 and looking for a Student Researcher for this summer. If you are at ICLR and is considering an internship reach out to me.

Spent two fully packed days in Singapore, gave two keynotes, one at ICLR which has 10 thousands people registered, and did two interviews afterwards. Hope that our work and effort will make young minds realize that there are still so much to learn and so much to discover about

Great to wrap up this #ICLR2025 trip with the presentation of IC-Light in the oral and poster sessions. Grateful to reconnect with brilliant minds in AI research! 🙌 Scaling In-the-Wild Training for Diffusion-based Illumination Harmonization and Editing by Imposing Consistent

Glad to be featured by this amazing list and thanks for the recognition #ForbesUnder30 #ForbesU30Asia Hope to continue to conduct in-depth research on AI for creativity and empower storytelling. The future of AI is not just about algorithms—it’s about people. Here’s to building

Amazing work!

Honored to be one of the HKUST cohort in Forbes 30 Under 30 Asia 2025🥳

Today we're releasing FLUX.1 Kontext - a suite of generative flow matching models that allow you to generate and edit images. Unlike traditional text-to-image models, Kontext understands both text AND images as input, enabling true in-context generation and editing.