Yiqun Mei
@myq_1997
Followers
125
Following
172
Media
4
Statuses
47
Research Scientist at @AdobeResearch; PhD @JHUCompSci; Former intern @Scanline_VFX @Adobe @epicgames @microsoft
Joined October 2015
This is a great move!.
We're excited to announce a second physical location for NeurIPS 2025, in Mexico City. By expanding our physical locations, we hope to address concerns around skyrocketing attendance and difficulties in obtaining travel visas that some attendees have experienced in the past few.
0
0
0
Playing #DeathStranding during weekend. @Kojima_Hideo is a real talent. Can’t wait for #DeathStranding2.
0
0
0
Have been reviewing top conferences papers for 5+ years. Most papers I reviewed in the past were like high school project with very little scientific value. And what worse is those papers are poorly written and unreadable. I have to spend many hours to understand what “technical.
0
1
5
RT @venturetwins: There's a new AI video model topping the leaderboard: Seedance. It's #1 in the @ArtificialAnlys ranking for text-to-vide….
0
176
0
I will be presenting this work tomorrow 4-6pm CDT @ ExHall D Poster #6. Come and chat if you are interested! #CVPR2025.
Congratulations to the research team at our sister company @eyelinestudios on their latest research paper - “Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset” - which will be presented at #CVPR2025 in Nashville.
0
0
3
I love this work so much- we not just improved the generation capability, but more importantly showed a way of leveraging the “thinking” ability in LLM for diffusion models and 2D visual generation. LLM is so powerful and I believe there will be a lot of new opportunities in.
💥 New paper: Think Before You Diffuse. Meet DiffPhy — LLM-guided, physics-aware video diffusion 🎥🧠🌍.SOTA on real-world motion & dynamics!.🔗 @JHUCompSci @HopkinsDSAI @HopkinsEngineer @myq_1997 #DiffusionModels #VideoGeneration
0
1
5
RT @vishalm_patel: 💥 New paper: Think Before You Diffuse. Meet DiffPhy — LLM-guided, physics-aware video diffusion 🎥🧠🌍.SOTA on real-world m….
0
23
0
RT @Scanline_VFX: Congratulations to the research team at our sister company @eyelinestudios on their latest research paper - “Lux Post Fa….
0
7
0
Yes, please be nice! Have seen a lot of disrespectful comments during the decision release day.
#KostasThoughts: When communicating with conference organizers, start by assuming good intentions and always keep it respectful. Remember, these are real people, volunteering their time and making personal sacrifices to bring everything together.
0
0
6
Love this. It’s good for the community.
#CVPR2025 Area Chairs (ACs) identified a number of highly irresponsible reviewers, those who either abandoned the review process entirely or submitted egregiously low-quality reviews, including some generated by large language models (LLMs). 1/2.
0
0
1
I have been waiting for an open sourced sora-level video generation model for a while. Here it finally comes!.
🚀 Announcing Wan2.1 - The Next Evolution in AI Video Generation!.We're thrilled to open-source our cutting-edge video generation suite！.#AIart #OpenSource.
0
0
0
RT @deepseek_ai: 🚀 DeepSeek-R1 is here!. ⚡ Performance on par with OpenAI-o1.📖 Fully open-source model & technical report.🏆 MIT licensed: D….
0
7K
0