tyler bonnen

neuroscientist @berkeley_ai. NIH K00 + UC Presidential Postdoctoral Fellow

[tyler bonnen @tylerraye]

excited to share some recent work!

tldr; models trained on multi-view sensory data are the first to match human-level 3D shape perception—all zero shot, with no training on experimental data/images

project page: https://t.co/cxTQQxfmO8

1/🧠

[Amil Dravid @_AmilDravid]

Scaling laws describe how loss changes with scale. Do neurons inside models change predictably too?

We study vision and language models up to 30B params and find systematic scaling in neuron universality, specialization, and selectivity.

Paper+code: https://t.co/1f1mQGnnZ4

1/n

[Stephanie Fu @xkungfu]

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

[Josh Wilson @Norcal_Neuro]

1/ New preprint with @dyamins + team! Ventral visual representations within areas evolve over the course of the response along the same hierarchical complexity axis that distinguishes the visual areas, potentially driven by local recurrence.
https://t.co/k9ugZYb9I9

[Yoon Bai @yoon_bai]

1/ How do we see 3D shape — for grasping, reaching, navigating — when the world is constantly in motion? We started with one piece of this puzzle—how the brain recovers surface geometry from dynamic input. New preprint, a joint effort from Josh Tenenbaum’s and Jim DiCarlo’s labs at MIT. (1/6)
https://t.co/1In72kZdTf

[David McAllister @davidrmcall]

We developed a simple, sample-efficient online RL technique for post-training image generation models. We see it as a possible steerable alternative to CFG, driven by any scalar reward, including human preference.

[A. Sophia Koepke @ASophiaKoepke]

New paper: Back into Plato’s Cave

Are vision and language models converging to the same representation of reality? The Platonic Representation Hypothesis says yes. BUT we find the evidence for this is more fragile than it looks.

Project page: https://t.co/aXsm7pY9VV

1/9

[Qianqian Wang @QianqianWang5]

The shell game is a fun challenge that cannot be solved by looking at a single frame. The model has to track every move, from the moment the object is hidden. Excited to share this!

[Imran Thobani @cogphilosopher]

1/ Most model-brain comparisons only ask: can the model predict the brain? — without also checking the reverse direction. When you map in both directions, differences between models emerge that were previously invisible. In prior work, we showed there's a deeper principle behind bidirectional mapping: we should compare models to brains the same way we compare real brains to each other 🧵

[Jennifer Listgarten @jlistgarten]

Our review on AI for protein engineering is out now, about this too-fast-moving field full of hype and overclaim, yet one that is having a real impact on the world and can be described in a coherent manner without histrionics
https://t.co/woOWuyTV5R

[Neerja Thakkar @neerjathakkar]

What’s the right representation for a world model? 3D, pixels, or something else?

Excited to release our new paper “Forecasting Motion in the Wild” where we propose point tracks as tokens for generating complex non-rigid motion and behavior

From @GoogleDeepmind @Berkeley_AI @TTIC_Connect

[Vongani Maluleke @vonekels]

When people share a space, their movements become intertwined. Embodied agents need to understand these social dynamics to interact effectively.

Introducing MAGNet 🧲, a unified autoregressive diffusion forcing model for multi-agent motion generation that captures these interactions.

MAGNet is flexible: predict the future, fill in missing motion, or have people react to each other, all while naturally scaling to N>2 people and generating ultra-long motion sequences.

[Stephanie Fu @xkungfu]

Excited to finally be releasing AutoGaze! Check it out https://t.co/abs3gyNoP9 (and 👀 the video demo)

[Baifeng @baifeng_shi]

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.

📄 https://t.co/GhbWZwMAg7
🌐 https://t.co/mEJ991MAIR
🤗 https://t.co/FOfc2QRThi

(1/n)🧵

[Roy Eyono @RoyEyono]

How do neural circuits in the brain implement normalization? 🧠

In our new paper, we show that just normalizing sensory input isn't enough. Crucially, we must also normalize the error signals! 🧵👇

Paper: https://t.co/IMZPSulQAH

[Amil Dravid @_AmilDravid]

I recently gave a talk at the AI@MIT reading group on our NeurIPS 2025 paper: https://t.co/cXDuIDkkks

We identify the neural mechanism behind attention sinks and propose a training-free mitigation.

Video: https://t.co/TrprZSRgY6
Slides: https://t.co/3L1Mud9c2M

[Junyi Zhang @junyi42]

𝗢𝗻𝗲 𝗺𝗲𝗺𝗼𝗿𝘆 𝗰𝗮𝗻’𝘁 𝗿𝘂𝗹𝗲 𝘁𝗵𝗲𝗺 𝗮𝗹𝗹.

We present 𝗟𝗼𝗚𝗲𝗥, a new 𝗵𝘆𝗯𝗿𝗶𝗱 𝗺𝗲𝗺𝗼𝗿𝘆 architecture for long-context geometric reconstruction.

LoGeR enables stable reconstruction over up to 𝟭𝟬𝗸 𝗳𝗿𝗮𝗺𝗲𝘀 / 𝗸𝗶𝗹𝗼𝗺𝗲𝘁𝗲𝗿 𝘀𝗰𝗮𝗹𝗲, with 𝗹𝗶𝗻𝗲𝗮𝗿-𝘁𝗶𝗺𝗲 𝘀𝗰𝗮𝗹𝗶𝗻𝗴 in sequence length, 𝗳𝘂𝗹𝗹𝘆 𝗳𝗲𝗲𝗱𝗳𝗼𝗿𝘄𝗮𝗿𝗱 inference, and 𝗻𝗼 𝗽𝗼𝘀𝘁-𝗼𝗽𝘁𝗶𝗺𝗶𝘇𝗮𝘁𝗶𝗼𝗻.

Yet it matches or surpasses strong optimization-based pipelines. (1/5)

@GoogleDeepMind @Berkeley_AI

[Micha Heilbron @m_heilb]

📢 PhD position in Developmental Language Modelling (plz RT🙏)

What can human language acquisition teach us about training language models? Join us as a PhD!

4 yrs, fully funded, MPI-NL; april 3

https://t.co/BCCap6MzPh

[tyler bonnen @tylerraye]

it's amazing working with @akanazawa and @JitendraMalikCV!!

manuscript: https://t.co/UiMdNuseqp
project page: https://t.co/mZWvgHl3d3
code: https://t.co/mrR0GniNiN
benchmark: https://t.co/kMLWkI8hnD

[tyler bonnen @tylerraye]

excited to share some recent work!

tldr; models trained on multi-view sensory data are the first to match human-level 3D shape perception—all zero shot, with no training on experimental data/images

project page: https://t.co/cxTQQxfmO8

1/🧠

[tyler bonnen @tylerraye]

these findings provide a computational bridge between cognitive theories and current practices in deep learning

we talk about some of these connections in the manuscript, but there are so many exciting questions to explore at the intersection of cog/comp/neuro science