Stephanie Fu
@xkungfu
Followers
571
Following
754
Statuses
326
PhD student @berkeley_ai | studying computer vision and intelligence | Previous: CS + Music @MIT
Berkeley, CA | Manhattan, KS
Joined February 2016
RT @akarshkumar0101: Very excited to share ASAL! Artificial Life aims to recreate natural evolution, but is severely bottlenecked by hand-…
0
27
0
unfortunately kansas has snapped out of its identity crisis as a subtropical region and has stopped selling pomegranates en masse this year. RIP to my post-NeurIPS pomegranate binges (2020-2023) gone but not forgotten
went home after #NeurIPS2023 and entered year 4 of "can stephanie eat 52 pomegranates before going back to school"
0
0
17
RT @sunjiao123sun_: Mitigating racial bias from LLMs is a lot easier than removing it from humans! Can’t believe this happened at the bes…
0
908
0
RT @dangengdg: I'll be presenting "Images that Sound" today at #NeurIPS2024! East Exhibit Hall A-C #2710. Come say hi to me and @andrewhowe…
0
8
0
RT @tylerraye: i'm in vancouver for #NeurIPS2024 presenting our 3D shape inference benchmark tomorrow! stop by poster #1210 at 4:30 on f…
0
6
0
Come by our poster #1302 Thursday morning at #NeurIPS2024 to chat!
I'm at #NeurIPS2024 this week! Excited to present our work on perceptual alignment with @xkungfu on Thursday morning (poster #1302). Please reach out if you want to chat about synthetic data, alignment, data-centric AI, representation learning, or anything else!
0
1
16
perks of joining @berkeley_ai compvision: meetings where you present on literally anything but research
This week in the @berkeley_ai CompVision meeting we did 5 min presentations: short powerpoint presentations about anything you want, as long as it isn't related to work. Here is a sampling of what transpired:
0
2
39
RT @ASophiaKoepke: We are hiring a PhD student to join us to work on computer vision / multi-modal learning in Munich @TU_Muenchen @MunichC…
0
84
0
RT @graceluo_: In a new preprint, we show that VLMs can perform cross-modal tasks... ...since text ICL 📚, instructions 📋, and image ICL 🖼️…
0
20
0
RT @lisabdunlap: 🧵We love measuring accuracy, but what about the vibes? Intro VibeCheck—a system that discovers and measures qualitative d…
0
37
0
Check out our new findings on perceptual alignment for vision models! Had a wonderful time collaborating with @shobsund doing a deep dive into this question 🥳
What happens when models see the world as humans do? In our #NeurIPS2024 paper we show that aligning to human perceptual preferences can *improve* general-purpose representations! 📝: 🌐: 💻: (1/n)
1
3
49
RT @mhamilton723: Come check out our latest work, Seeing Faces in Things, which studies #pareidolia in humans and #AI. We will be presentin…
0
6
0
RT @Cinnabar233: How can you scale up robot learning? We introduce HOP: Extract hand-object trajectories from in-the-wild videos. Train a…
0
38
0