Stephanie Fu

@xkungfu

PhD student @berkeley_ai | Previous: CS + Music @MIT | underfit to the demands of reality

Berkeley, CA | Manhattan, KS

stephanie-fu.github.io

Replies Reposts Media

Pinned
Stephanie Fu
@xkungfu
Mar 24
Excited to finally be releasing AutoGaze! Check it out autogaze.github.io (and 👀 the video demo)
Baifeng
@baifeng_shi
Mar 24
Humans can see in high-res, high-FPS in real-time. Why can't VLMs? Introducing AutoGaze: ViTs/VLMs "gaze" only at key video regions! Up to 4-100x token savings, 19x speedup, and enables scaling to 4K-res 1K-frame videos. 📄 arxiv.org/abs/2603.12254 🌐 autogaze.github.io 🤗
00:00
2
Stephanie Fu
@xkungfu
Aug 18
Building a metric that allows conditioning on different senses of similarity (especially in this free-form way) has been a bit of an aspiration of mine 😅 amazing results, well done to the team!
Sheng-Yu Wang
@ShengYuWang6
Aug 18
How similar are two images? Prior metrics (e.g., LPIPS, DreamSim) give just a single score. But actually, there are multiple *senses* of similarity (color, pose, etc.) We introduce TPIPS -- Text-Prompted Image Perceptual Similarity "pip install tpips" peterwang512.github.io/TPIPS 🧵
00:00
Stephanie Fu
@xkungfu
Jun 3
I'm at #CVPR2026 presenting our ✨AutoGaze highlight✨ with @baifeng_shi this week! - talk @ GAZE workshop (🗓️Thurs 2:30p📍room 711) - poster #258 (🗓️Sat 11:45a📍Exhibit Hall F) stop by or reach out to chat about vision+cogsci and modeling human vision :D
Baifeng
@baifeng_shi
Mar 24
Humans can see in high-res, high-FPS in real-time. Why can't VLMs? Introducing AutoGaze: ViTs/VLMs "gaze" only at key video regions! Up to 4-100x token savings, 19x speedup, and enables scaling to 4K-res 1K-frame videos. 📄 arxiv.org/abs/2603.12254 🌐 autogaze.github.io 🤗
00:00
Stephanie Fu
@xkungfu
Feb 16
submit to our re-align challenge 😊🚀!
Badr AlKhamissi
@bkhmsi
Feb 16
🚀 The Re-Align Challenge is now LIVE! We’re inviting you to explore what properties of vision models and data lead to convergences and divergences in representational alignment. 🔗 Get started: huggingface.co/spaces/represe… 🧵👇
Stephanie Fu
@xkungfu
Jan 23
📝 submit to Re-Align at ICLR 2026, and check out our new challenge!
Badr AlKhamissi
@bkhmsi
Jan 7
🎉 Re-Align is back for its 4th edition at ICLR 2026! 📣 We invite submissions on representational alignment, spanning ML, Neuroscience, CogSci, and related fields. 📝 Tracks: Short (≤5p), Long (≤10p), Challenge (blog) ⏰ Feb 5, 2026 for papers 🔗 representational-alignment.github.io/2026/