Yifan Chen

Assistant professor of mathematics @UCLA. Previously @NYU_Courant @Caltech @Tsinghua_Uni.

[Stat.ML Papers @StatMLPapers]

Delocalization of bias in unadjusted Hamiltonian Monte Carlo and underdamped Langevin https://t.co/QiFIE42Dce

[Furong Huang @furongh]

Everyone is trying to make LLMs “think longer.” But what if the next leap in reasoning is not more thoughts…
…but knowing which thought to commit first?
Our new paper studies this question in diffusion language models.
Introducing SAS: Self-Aware Scheduling.

#ICML2026
#LLMReasoning #DiffusionModels

https://t.co/kZRT9KwMHG
🧵

[Oratomic, Inc. @TeamOratomic]

Today, we introduce Oratomic.

We are on a focused mission to build the world’s first fault-tolerant quantum computers and unlock their transformative applications. Quantum computers offer a fundamentally new way of understanding and interacting with the physical world.

Our recent scientific advance finds that Shor’s algorithm is possible with as few as 10,000 reconfigurable atomic qubits: https://t.co/VS6Ste00fC

Our team integrates world-class expertise in quantum error correction, neutral atom systems, artificial intelligence, and optical engineering. We are working together to make fault-tolerant quantum computing a reality.

To learn more about Oratomic and our team, visit https://t.co/Pjtg9n2R2P

[Monte Carlo Seminar @OnlineMCSeminar]

Monte Carlo meets randomized linear algebra! Join us next Tuesday, February 3, 2026, for a talk by Ethan N. Epperly. Learn how Monte Carlo ideas improve large-scale computation, variance reduction, and hard sampling problems. Zoom link on event page. #MonteCarlo

[Jingfeng Wu @uuujingfeng]

Together with @yuxiangw_cs and Maryam Fazel, we are excited to present our tutorial "Theoretical Insights on Training Instability in Deep Learning" tomorrow at #NeurIPS2025!
Link: https://t.co/e4T1eI45Ql
*picture generated by Gemini

[Chieh-Hsin (Jesse) Lai @JCJesseLai]

Tired to go back to the original papers again and again? Our monograph: a systematic and fundamental recipe you can rely on!

📘 We’re excited to release 《The Principles of Diffusion Models》— with @DrYangSong, @gimdong58085414, @mittu1204, and @StefanoErmon.

It traces the core ideas that shaped diffusion modeling and explains how today’s models work, why they work, and where they’re heading.

🧵You’ll find the link and a few highlights in the thread.
We’d love to hear your thoughts and join some discussions!

⚡ Stay tuned for our markdown version, where you can drop your comments!

[Ernest Ryu @ErnestRyu]

I used ChatGPT to solve an open problem in convex optimization.

*Part I*

(1/N)

[Ethan Epperly @ethanepperly]

New paper out with Chris Camaño, Raphael Meyer, and Joel Tropp re-examining sketching algorithms! Included: subspace injections as an alternative to subspace embeddings, the theory and practice of sparse sketching, tensor sketching, and much more! https://t.co/gq6z1CKsRW

[Statistics (Machine Learning) Papers @StatsPapers]

Lipschitz-Guided Design of Interpolation Schedules in Generative Models. https://t.co/d8a8GRWHBw

[Stat.ML Papers @StatMLPapers]

Scale-Adaptive Generative Flows for Multiscale Scientific Data https://t.co/LuB2HXSzVS

[Banghua Zhu @BanghuaZ]

Excited to share that I’m joining NVIDIA as a Principal Research Scientist!

We’ll be joining forces on efforts in model post-training, evaluation, agents, and building better AI infrastructure—with a strong emphasis on collaboration with developers and academia. We’re committed to open-sourcing our work and sharing it with the world. Let’s build a stronger, more open AI community together!

[Stat.ML Papers @StatMLPapers]

New affine invariant ensemble samplers and their dimensional scaling https://t.co/YyQuLJbCbD

[Stat.ML Papers @StatMLPapers]

Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias https://t.co/AkrONijLcX

[Yifan Chen @yifanc96]

@OwhadiGroup @HoumanOwhadi And also the recent progress for scaling up to millions of data by preconditioning! See https://t.co/SklvYTrPJg

[Ethan Epperly @ethanepperly]

New paper out with @mateodd25, Zach Frangella, Joel Tropp, and Rob Webber on randomized preconditioners for kernel ridge regression! Our goal was to develop simple preconditioners that are robust to different parameter choices for the kernel model https://t.co/W4Pptnj0Zw

[Yifan Chen @yifanc96]

@OwhadiGroup @HoumanOwhadi For scientific computing problems in high dimensional physical space, such as chemistry, Cholesky factorization can also work very well! Keep an eye on the randomly pivoted Cholesky that uses randomness to discover low rank structures effectively https://t.co/LelyLDAVuu

[Houman Owhadi Group @ Caltech @OwhadiGroup]

https://t.co/oBbng4DmrB Provably accelerating Gaussian process and kernel methods to near-linear complexity, even with derivative information, such as in solving PDEs! By @yifanc96 @HoumanOwhadi and FlorianSchaefer

[Ethan Epperly @ethanepperly]

New preprint up about a simple, efficient, and (surprisingly) effective algorithm for positive semidefinite (psd) low-rank approximation joint with @yifanc96, Joel Tropp, and Robert Webber 1/4 https://t.co/ZfWwM30RKB

[Yifan Chen @yifanc96]

@OwhadiGroup Thank you all!

[Houman Owhadi Group @ Caltech @OwhadiGroup]

@yifanc96 successfully passed his candidacy today with his talk on Numerical Computation via Inference! Congratulations, Yifan!