tyler bonnen
@tylerraye
Followers
1K
Following
3K
Statuses
542
neuroscientist @berkeley_ai. NIH K00 + UC Presidential Postdoctoral Fellow. he/him
Unceded Muwekma Ohlone Land
Joined August 2020
do large-scale vision models represent the 3D structure of objects? excited to share our benchmark: multiview object consistency in humans and image models (MOCHI) with @xkungfu @YutongBAI1002 @thomaspocon @_yonifriedman @Nancy_Kanwisher Josh Tenenbaum and Alexei Efros 1/👀
13
89
415
@GretaTuckute @mitbrainandcog @ev_fedorenko @Nancy_Kanwisher @JoshHMcDermott @yoonrkim @mcgovernmit congratulations 🥳 and so excited to hear about whats coming next ✨
1
0
6
i'm in vancouver for #NeurIPS2024 presenting our 3D shape inference benchmark tomorrow! stop by poster #1210 at 4:30 on friday if you're interested and if you'd like to talk about neuro-ai, human cognition, or suggest nearby hikes, feel free to reach out!
do large-scale vision models represent the 3D structure of objects? excited to share our benchmark: multiview object consistency in humans and image models (MOCHI) with @xkungfu @YutongBAI1002 @thomaspocon @_yonifriedman @Nancy_Kanwisher Josh Tenenbaum and Alexei Efros 1/👀
0
6
66
happy to share that we'll be presenting this work at neurips 2024! 🥳 some *surprising* updates coming for the results soon 👀 but all the code/images/data are already available at project page: 🤗: code:
do large-scale vision models represent the 3D structure of objects? excited to share our benchmark: multiview object consistency in humans and image models (MOCHI) with @xkungfu @YutongBAI1002 @thomaspocon @_yonifriedman @Nancy_Kanwisher Josh Tenenbaum and Alexei Efros 1/👀
3
19
141
1
0
2
@lukas_mut @xkungfu @YutongBAI1002 @thomaspocon @_yonifriedman @Nancy_Kanwisher perfect! good luck with your submission
0
0
1
@abhinav1kumar i'd guess the ordering relates to different readouts: they use a dense multi-scale decoder while we're using a lightweight classifier. CLIPs are probably better suited for our lightweight readouts then MAEs. but curious what @_mbanani thinks about this!
1
0
4
0
0
1
0
0
0
0
0
0
@StphTphsn1 @xkungfu @YutongBAI1002 @thomaspocon @_yonifriedman @Nancy_Kanwisher thanks Stephane! and of course!!! always happy to point people towards your work; we are some of the very few people who are thinking about how temporal dynamics/processing time relate to human/model mis-alignment ✨
0
0
3
@mariam_s_aly @xkungfu @YutongBAI1002 @thomaspocon @_yonifriedman @Nancy_Kanwisher ah, thank you Mariam!!! the acronym took a while 😅
0
0
1
0
0
1
@recursus @xkungfu @YutongBAI1002 @thomaspocon @_yonifriedman @Nancy_Kanwisher thanks Dan—would love to know what you think!
0
0
0
we're excited for others to build on our work! paper, code, images, and behavioral data are at: paper: code: 🤗: project page: 10/10
0
0
14
why might time be important for humans? when looking at an image (top row) people reliably attend to specific visual features (middle row) whereas model attention (bottom row) is more uniformly distributed these gaze dynamics provide clues about how we outperform models 9/10
1
0
11