🇿🇦 || AI Graduate Researcher @berkeley_ai || Advisors: @JitendraMalikCV and @akanazawa || Research Interest: 3D Vision, Generative Models & AI for social good
Berkeley, California
- Tweets 140
- Following 213
- Followers 440
- Likes 158
Pinned Tweet
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.
8
58
371
67,658
Vongani Maluleke retweeted
Today, we’re introducing [schema]: a harness reaching 99% RHAE with Opus 4.8 + Fable 5 and 95.35% with GPT-5.6 Sol on ARC-AGI-3 Public set.
[schema] makes an LLM think like a physicist. 🧵
126
293
2,487
967,551
Vongani Maluleke retweeted
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: akoepke.github.io/cave_umwel…
1/9
6
68
342
91,252
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.
8
58
371
67,658
Grateful for my amazing collaborators: @kiehoriuchi, @LeaMue27, Evonne Ng, @JitendraMalikCV, and @akanazawa
Check out our paper, project page and code for more details:
📎Paper: arxiv.org/abs/2512.17900
🌐Page: von31.github.io/MAGNet
🖥️ Code: github.com/Von31/MAGNet-code
2
27
22,510
Thanks @lisabdunlap for organizing a long overdue talk.
-----Biltong Vs Beef Jerky Poll Results------
They came.
They chewed.
They voted.
Biltong got 75% — Swi nandzika ngopfu!!
Why have a dissertation when you can have a DESSERTation? Thanks to @vonekels for co leading this joke talk and our advisors @profjoeyg and @akanazawa for introducing us just like a real dissertation (although to be fair Joey thought this was my actual defense)
2
1
7
1,428
Vongani Maluleke retweeted
Happy to share our new work on Navigation World Models! 🔥🔥
Navigation is a fundamental skill of agents with visual-motor capabilities. We train a single World Model across multiple environments and diverse agent data.
w/ @GaoyueZhou, Danny Tran, @trevordarrell and @ylecun.
5
58
275
83,826
Vongani Maluleke retweeted
We wrote a paper: estimating body and hand motion from a pair of glasses! 👓
website: egoallo.github.io
code: github.com/brentyi/egoallo
16
120
733
98,356
To what extent does social interaction affect behavior in couples swing dancing?
Our work looks at how we can predict a dancer's next moves based on their past motion alone or by considering both the dancer's and their partner's motions. 🪩🕺🏾 🆚 🪩🕺🏾💃🏾
🧵1/6
10
22
113
22,303
Sampling multiple predictions👯👯👯 from our model shows that knowing about the "other" helps generate diverse motion that is closer to the ground truth.
🧵5/6
1
3
1,668
Please see the website for more details.
synNsync🪩is joint work with my awesome ✨co-authors✨:
@LeaMue27 @jathushan @geopavlakos @shiryginosar @akanazawa @JitendraMalikCV
Website🖥️: von31.github.io/synNsync/
Data💾: github.com/Von31/swing_dance…
Arxiv📜: arxiv.org/abs/2409.04440
🧵6/6
2
25
17,654
Vongani Maluleke retweeted
Super excited to share that I will be starting as an Assistant Professor at UT Austin @UTCompSci in January 2024! 🥳🥳
I'm extremely grateful to my amazing mentors and colleagues for their unwavering support every step of the way!
Looking forward to this exciting new chapter!
56
11
450
64,635
Vongani Maluleke retweeted
While most existing methods that estimate 3D human pose and shape (HPS) do so in camera coordinates, many applications require 3D humans in global coordinates. At #CVPR2023, we introduce TRACE, which addresses this using a novel 5D representation. 1/6
4
58
284
58,723
Vongani Maluleke retweeted
I'll be talking about nerfstudio at #GTC2023 today at 2pm PT!
Come learn about #NeRFs, the latest updates in @nerfstudioteam, and see cool results from the community 🥳
bit.ly/3lzhtTU
2
9
96
16,382
Vongani Maluleke retweeted
I delivered the 110th Annual Martin Meyerson UC Berkeley Faculty Research Lecture on March 20, 2023. piped.video/watch?v=f6fDpKDx…
10
25
264
94,352
Vongani Maluleke retweeted
Psyched to finally release our new work that decouples human🧑🏽🤝🧑🏻 & camera motion🎥 from an unconstrained video✨
We place people in the world, enabling high quality recovery of motion and spatial relationships between people 🤼 CVPR'23:
Code & more video: vye16.github.io/slahmr
11
84
553
86,171
Vongani Maluleke retweeted
By the way - if you are a journalist looking to make sense of the bias issues with generative AI, I highly recommend speaking to those that have been thinking about this much longer than I have: @vonekels for example has an excellent paper on bias in face generation models.
We’ll be presenting our Bias in GANs work at @eccvconf on 25/10 at 15:30.
One of our findings ~ Truncation commonly used to improve image quality in GANs, decreases racial diversity of generated images. Paper link: arxiv.org/abs/2209.02836
#ECCV2022 @berkeley_ai @Berkeley_EECS
4
9
49
9,411