Renjie Liao

Fullmetal Alchemist of Deep Learning

[Renjie Liao @lrjconan]

We show that Gaussian RBMs can generate good images just like other generative models, despite the single-layer architecture. Key innovations:
1) Gibbs-Langevin sampling;
2) modified Contrastive Divergence.
Paper: https://t.co/pZk1TDzpfR
Code: https://t.co/u6ZNVOrZww
1/2

[Jason Lee @jasondeanlee]

A Chinese-American hero that inspired my parents' generation to study and stay in America.

[Renjie Liao @lrjconan]

@bose_joey @imperialcollege @ICComputing Congrats, Joey!!

[Felix (Yuxiang) Fu @felix_yuxiang]

Interested in how to generate realistic human trajectories using diffusion with just one step🤔?

This is now possible with MoFlow, a one-step Flow Matching method accompanied with Implicit Maximum Likelihood Estimation based distillation.

🚀 Join us at #CVPR2025 in Nashville!

[Renjie Liao @lrjconan]

If you’ll be at CVPR, come check out our work LatentHOI on hand–object manipulation!
📍 Poster Session 4, #155
📅 Saturday

[Muchen Li @LiJonassen]

Want to generate realistic hand–object manipulations for unseen objects?

Check out our new paper: "LatentHOI: On the Generalizable Hand Object Motion Generation with Latent Hand Diffusion".

Appearing at #CVPR2025 in Nashville!

[Renjie Liao @lrjconan]

🚀Our new work (RetroSynFlow) on retrosynthesis:
1) SOTA discrete flow matching that leverages synthons: products->synthons->reactants
2) effective test-time reward steering

Led by my amazing students @RobinY798, @qi_yan98, with stellar collaborators Guy Wolf & @bose_joey

[Robin Yadav @RobinY798]

Excited to announce RetroSynFlow, a discrete flow matching framework for diverse and accurate retrosynthesis!

📄Paper available here: https://t.co/Z4mgEfdjES

Joint work w/ @qi_yan98 , Guy Wolf, @bose_joey and @lrjconan .

👇 A quick overview 🧵

[Renjie Liao @lrjconan]

Led by my undergrad intern Nick Zhang (@VectorInst) and my PhD student Donglin Yang @ydlin718 at @ECEUBC.
Huge shoutout to them for driving this forward! 🙌

Code: https://t.co/dmiTi7Or2i
Paper: https://t.co/GgIs2HsKJS

[Renjie Liao @lrjconan]

Ever wondered how card shuffling can help solve combinatorial problems like sorting, jigsaw puzzles, or TSPs?

Our ICLR 2025 (Oral) paper SymmetricDiffusers introduces a novel discrete diffusion model on finite symmetric groups to solve them in a unified and principled way!

[Renjie Liao @lrjconan]

7/ More results on sorting and TSPs.

[Renjie Liao @lrjconan]

Interested in LLMs for math reasoning? Check out our new work that builds 647K Math QA pairs and A Live Math Benchmark that is kept up-to-date, led by my brilliant students @sadegh_mahdavi4 @LiJonassen and Kaiwen!

[Muchen Li @LiJonassen]

🚀 Training an LLM for math reasoning, but high-quality data is scarce and costly?

Check out our paper: “Leveraging Online Olympiad-Level Math Problems for LLM Training & Contamination-Resistant Evaluation.” 📖✨
TL;DR:
🔹 LLM-powered pipeline for scalable, high-quality data collection 🤖
🔹 647K Math QA pairs 📊
🔹 A Live Math Benchmark that is kept up-to-date⏳

Paper: https://t.co/sTmiWn8aAj
Code & Data: https://t.co/qy3NKOlvlY
Project Website: https://t.co/ER84nE1x34
Evaluation Leaderboard: https://t.co/K73k65LAFM
@askalphaxiv (for QA): https://t.co/aE0RDdz4gF

[Renjie Liao @lrjconan]

It means a lot to someone who has worked on Hopfield networks and Boltzmann machines. John and Geoff's foundational work has inspired generations of scientists, and it will keep doing so! I now have a compelling reason to keep teaching and researching these models! Huge Congrats!

[The Nobel Prize @NobelPrize]

BREAKING NEWS
The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”

[Renjie Liao @lrjconan]

Welcome to submit your work to NeurIPS 2024 workshop on Adaptive Foundation Models!
Deadline: Oct. 4 AOE
https://t.co/RYimmmOpPJ

[Paul Vicol @PaulVicol]

⌛️We extended the submission deadline for the NeurIPS 2024 Workshop on Adaptive Foundation Models to October 4 AoE!

🏁Submission site: https://t.co/ZYcMeDyW1q

🌐Website: https://t.co/223K7rgD4W

Organizers: @mengyer, @PaulVicol, @NailaMurray, @lrjconan, @BeidiChen, @weichiuma

[Renjie Liao @lrjconan]

@yanii Congrats Yani!!

[Renjie Liao @lrjconan]

@bose_joey @mcgillu @Mila_Quebec @prakash127 @gauthier_gidel Big congrats, Joey!

[Renjie Liao @lrjconan]

@weichiuma @Cornell @CornellCIS @RaquelUrtasun @HoiemDerek @vincesitzmann Congrats!! Prof. Ma!