PhD student @PrincetonCS, undergrad @columbia
Princeton, NJ
Joined March 2021
- Tweets24
- Following98
- Followers124
- Likes247
Arnold Caleb Asiimwe retweeted
Introducing Langevin Flow Maps
TLDR: Neural Network Potentials that learn their own stochastic pathwise solution for faster simulation.
- Transferable across molecular systems.
- Transition dynamics are preserved.
- No trajectory data are required.
Work together with @sgmccallum, supervised by @AlexanderTong7, and @JamesFosterBath.
Arxiv: arxiv.org/abs/2610.05998
Data: huggingface.co/datasets/nikl…
Code: github.com/sammccallum/lfm
Arnold Caleb Asiimwe retweeted
Introducing SCALLOP 💜 Our new paper accepted at NeurIPS 2026 🐨
🚀 A scalable, efficient way to train few-step likelihood-available flow maps, enabling effective Boltzmann generation!
📽️ project page: tonyauyeung.github.io/scallo…
🔗 paper: arxiv.org/pdf/2606.29110
Arnold Caleb Asiimwe retweeted
Do vision-language models actually lack visual understanding, or are they held back by their learned priors?
In our #NeurIPS2026 paper, we find that in-context learning can help VLMs overcome misleading priors, improving accuracy by up to 27%.
🔗 arxiv.org/abs/2610.12942
Arnold Caleb Asiimwe retweeted
The most profound paper of my PhD so far. We truly did something special to make LMs play/explain chess, needing both architectural & algorithmic innovation (natural-language analogue of the Alphazero algorithm) + applicable to many other domains. Please read on and share!
1/10
I learned so much working on this project, and I’m excited to share this work! Joint work with @YangWilliam_, @SanghyukChun, Esin Tureci and @orussakovsky . Thanks also to Timothy Buschman, @ryan_p_adams, members of @VisualAILab for helpful discussions and feedback.
Paper: alphaxiv.org/abs/2610.03626
Code: github.com/princetonvisualai…
Code and checkpoints will be released soon!
4/ we also show that by making depth as time explicit and treating depth as its own flow, a shared, time-conditioned block can learn to denoise across layers. Distilling the teacher’s layerwise computation this way enables aggressive parameter compression.
3/ this progression depends on the transport task e.g., when mean flows predict a noisy intermediate endpoint, the layerwise predictions first reveal cleaner image structure, then renoise toward the requested endpoint, all within one forward pass.
1/ I’m excited to share our work on “Depth as Time in One-Step Generative Models”!
alphaxiv.org/abs/2610.03626
TL;DR: We ask, when a model learns to generate an image in one forward pass, what happens to the denoising process? We observe that process unfolding over depth!
Arnold Caleb Asiimwe retweeted
Today, agents execute isolated tasks. Tomorrow, agents will steer complex decisions across long horizons.
Introducing CEO-Bench, a first step to measure "Steering Intelligence." In CEO-Bench, agents are asked to run a simulated startup for 500 days.
ceobench.com
Arnold Caleb Asiimwe retweeted
🥳Thank you to everyone who joined our #CVPR2026 tutorial, “The Principles of Diffusion Models: Real-Time Continuous & Discrete Diffusion”!
This event wouldn’t have been possible without all the participants, our amazing speakers (@ssahoo_ & @mittu1204), and the organizers (@gimdong58085414 & @DrYangSong & @StefanoErmon & @CVPR) who helped make it happen.
Grateful for the great energy and discussions!
📢 @CVPR 2026 Tutorial
We’re turning our book 《The Principles of Diffusion Models》 into a live tutorial at #CVPR2026！
Part I · Continuous Diffusion — by me 👋
🎯 First-principles & intuitive view of diffusion
🎯 Fast generators & flow maps
🎯 Audio-visual content creation & protection — by @mittu1204
🔗 Link to our book: the-principles-of-diffusion-…
Part II · Discrete Diffusion — by @ssahoo_
🎯 The first tutorial crafted for discrete diffusion
Co-organizers: @StefanoErmon @DrYangSong @gimdong58085414
Full schedule + details 👇
Arnold Caleb Asiimwe retweeted
Video models surprisingly can solve mazes, but inconsistently. We understand little about how they reason, making it hard to use such abilities.
We investigate the denoising process and find models commit to a plan early, letting us screen far more candidates for better perf.
🧵
Arnold Caleb Asiimwe retweeted
We present🌊AquaBot🤖: a fully autonomous underwater manipulation system powered by visuomotor policies that can continue to improve through self-learning to perform tasks including object grasping, garbage sorting, and rescue retrieval.
aquabot.cs.columbia.edu
more details👇
Arnold Caleb Asiimwe retweeted
At #ECCV2024, we presented Minimalist Vision with Freeform Pixels, a new vision paradigm that uses a small number of freeform pixels to solve lightweight vision tasks. We are honored to have received the Best Paper Award!
Check out the project here: cave.cs.columbia.edu/project…
Arnold Caleb Asiimwe retweeted
🚨 New paper! 🚨
We solve lots of tasks posed in words by thinking visually. Can LLMs? Not in text, but we can unlock this ability with images!
Introducing whiteboard-of-thought, enabling MLLMs to express intermediate reasoning as images via code!
🔗 huggingface.co/papers/2406.1…
🧵
Arnold Caleb Asiimwe retweeted
Organizing the first NYC vision workshop was super fun! Shout out to other organizers @elliottszwu @Haian_Jin and especially @Jimantha for the generous support! – at New York, NY
Arnold Caleb Asiimwe retweeted
Carl Vondrick (@cvondrick) is looking for PhD students who are interested in computer vision and machine learning. To learn more about him -bit.ly/vondrick. For info on our #PhD programs bit.ly/CSPhDprogram. The deadline to apply is December 15.
