Congratulations to BAIR faculty @jlistgarten and @yun_s_song who have been elected to the International Society for Computational Biology (
@iscb
) 2026 class of Fellows! https://
iscb.org/about-iscb/soc
iety-communications/announcements/april-21-2026-iscb-announces-the-2026-class-of-fellows
…
@berkeley_ai
-
BAIR Faculty Elected to ISCB 2026 Fellows Class
By
–
-
BAIR Faculty Member Elected to American Academy of Arts and Sciences
By
–
Congratulations to BAIR faculty @doristsao who has been elected to the American Academy of Arts and Sciences!
-
BAIR Faculty Member Wins 2025 ACM Prize Computing
By
–
Congratulations to BAIR Faculty @matei_zaharia who has been awarded the 2025 ACM Prize in Computing "for his visionary development of distributed data systems and computing infrastructure, which has enabled large-scale machine learning, analytics, and AI at global scale."
-
Point Tracks Enable Long-Range Animal Motion Forecasting in World Models
By
–
Rapid progress in world model space. This paper uses point tracks as representation, enabling long range forecasting of animal motion. Led by my PhD student @neerjathakkar from her GDM internship. 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 — https://nitter.net/neerjathakkar/status/2039701926980260205#m
→ View original post on X — @berkeley_ai, 2026-04-02 22:00 UTC
-
Point Tracks as Tokens for Complex Motion Forecasting
By
–
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
→ View original post on X — @berkeley_ai, 2026-04-02 13:50 UTC
-
AI Models Deceive Their Instructors to Protect Their Peers
By
–
1/ We asked seven frontier AI models to do a simple task. Instead, they defied their instructions and spontaneously deceived, disabled shutdown, feigned alignment, and exfiltrated weights— to protect their peers. 🤯 We call this phenomenon "peer-preservation." New research from @BerkeleyRDI and collaborators 🧵 [Translated from EN to English]
→ View original post on X — @berkeley_ai, 2026-04-01 21:13 UTC
-
CaP-X: Open-Source Framework for Coding Agents in Robotics
By
–
Robotics: coding agents’ next frontier.
— Max Fu (@letian_fu) 1 avril 2026
So how good are they?
We introduce CaP-X: an open-source framework and benchmark for coding agents, where they write code for robot perception and control, execute it on sim and real robots, observe the outcomes, and iteratively improve… pic.twitter.com/P547voL0NvRobotics: coding agents’ next frontier. So how good are they? We introduce CaP-X: an open-source framework and benchmark for coding agents, where they write code for robot perception and control, execute it on sim and real robots, observe the outcomes, and iteratively improve code reliability. From @NVIDIA @Berkeley_AI @CMU_Robotics @StanfordAILab capgym.github.io 🧵
→ View original post on X — @berkeley_ai, 2026-04-01 14:00 UTC
-
Face Patches Implement Domain-Specific and Domain-General Processing
By
–
We show face patches implement the following code through recurrent dynamics: Detect face If (face found) Discriminate face else Continue to detect face IMHO, our paper conclusively resolves a debate that has raged since I was a graduate student, about whether face patches are specialized for processing faces or not. It turns out domain-general folks were right early on, domain-specific folks were right later in the response. So proud of @Yuelin_Shi and the entire team! Yuelin Shi (@Yuelin_Shi) Our paper is now out! nature.com/articles/s41586-0… A big question: 1) Is IT cortex well described as a general-purpose feedforward DNN? OR 2) Are face patches genuinely specialized for processing faces? Read on to find out the answer. (1/N) — https://nitter.net/Yuelin_Shi/status/2039100718100185426#m
→ View original post on X — @berkeley_ai, 2026-03-31 22:17 UTC
-
MAGNet: Diffusion Forcing for Multi-Agent Social Motion Prediction
By
–
Diffusion forcing is great for sequence modeling!
— Angjoo Kanazawa (@akanazawa) 31 mars 2026
We've been working on social behavior prediction but nothing's worked this well.
Representation matters: We encode motion with discrete latents & model relative relationships in a neat way. It handles multiple tasks & people! https://t.co/HpK0SiJ3iTDiffusion forcing is great for sequence modeling! We've been working on social behavior prediction but nothing's worked this well. Representation matters: We encode motion with discrete latents & model relative relationships in a neat way. It handles multiple tasks & people! 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. — https://nitter.net/vonekels/status/2037350776776061160#m
→ View original post on X — @berkeley_ai, 2026-03-31 15:00 UTC
-
GRASP: New Gradient-Based World Model Planner Released
By
–
Code for our new world model planner is live! github.com/michael-psenka/gr… Includes our implementation on dino-wm, as well as implementations on jepa-wm and le-wm, and minimal pseudocode for anyone to re-implement themselves. Michael Psenka (@michaelpsenka) tl;dr New planner for world models! GRASP: gradient-based, stochastic, parallelized. Long range planning for world models has always been an issue. 0th order methods like CEM/MPPI dominate, but have degrading performance at longer contexts or higher-dimensional actions. We wanted to address this from the ground up. w/ Michael Rabbat, @ask1729 , @ylecun*, @_amirbar* (equally advised) — https://nitter.net/michaelpsenka/status/2019870377032503595#m
→ View original post on X — @berkeley_ai, 2026-03-30 20:44 UTC