UIUC CS PhD Student
United States
Joined September 2018
- Tweets12
- Following11
- Followers9
- Likes18
Yifan Shen retweeted
Omni models often answer social questions by leaning on the wrong modality or reading the wrong moment in the clip. CogniRoute trains MoE routing to follow the evidence, which modality to trust, and when the cue occurs.
+15.3 pts over the best closed-source model on social video QA 🧵1/4
Yifan Shen retweeted
That's a wrap! We successfully organized the 2nd Workshop on Computer Vision for Children (CV4CHL) at #CVPR2026. 🚀
A massive thank you to our keynote speakers (@sanmikoyejo, Dr. Jean-Marc Odobez @Idiap_ch, @dimadamen, @RehgJim) and panelists (@BoqingGo, @YapengTian, @yutian0207) for their incredible talks!
We are also delighted to announce this year's Best Paper Award goes to Dr. Carlos Caetano (Universidade Estadual de Campinas). 🏆 Congratulations!
Special thanks to @RehgJim (UIUC HCESC) and @pediamedai for their generous sponsorship, and to Dr. Adam Cross, Yifan Shen, and @Ismini_L for their invaluable support in hosting the workshop! 🤝
Can AI really think like a doctor? 🩺🤖
We're launching MDLE, the ultimate medical AI benchmark by @UIUC, @penn, @fudan, and @NUSingapore.
🎁 Reward: Submit a case and earn Co-authorship on our upcoming paper!
(1/3) 👇
🤖 Made with AI
We want the cases that kept you up at night. 🧠
✅ Real-world & Multimodal (Labs/Imaging) 📸
✅ Multi-step clinical reasoning 🧬
✅ AI currently fails or struggles ❌
No coding required—just your clinical brain. 👨⚕️👩⚕️
(2/3) 👇
Help us test the limits of AI before it hits the clinic. 🚀
📷 First round deadline: July 31, 2026 📷
app.pediamed.ai Join the mission to define the future of #MedicalAI! 📷 (3/3)
Yifan Shen retweeted
🚀 Call for Papers & Challenge: CV4CHL @CVPR 2026 in Denver! 🏔️
We’re bridging the gap in Computer Vision for children’s health, education & development. Join us! 👶💻
🏆 Children's Gait Competition: Win an NVIDIA RTX 5080 GPU or Latest AR Glasses! 🎮🔥
📅 Deadlines (AoE):
• Proceeding Papers: Mar 10
• Non-Proceeding: May 10
• Challenge Submission: May 10
🔗 Details & Submission: pediamedai.com/cv4chl
+ A fantastic keynote speaker lineup! 🤩
#CVPR2026 #ComputerVision #AIforGood #NVIDIA #RTX5080 #MedAI #CV4CHL
Yifan Shen retweeted
🚀🚀Reasoning Meets 3D! CoRe3D is now released! 🤩🤩A collaborative reasoning 3D framework that unifies understanding, generation, and editing 💯
It can synthesize from complex or indirect prompts.😮⬇️
📄arxiv.org/abs/2512.12768
🌐plan-lab.github.io/projects/…
SpatialReasoner-R1 is now released! 🚀
Can Large Language Models truly understand and navigate the physical world? While LLMs have mastered logic and coding, complex spatial reasoning—interpreting 3D structures, relative orientations, and navigation—remains a bottleneck.
🔗 Project Page: plan-lab.github.io/projects/…
💻 GitHub: github.com/PLAN-Lab/SpatialR…
🤗 Hugging Face: huggingface.co/PLAN-Lab/Spat…
