Bayesian Methods Research Group retweeted
๐จ Did you know neural networks can behave like literal ideal gases? ๐จ
In our #IJCAI2026 paper, we show that at stationarity, scale-invariant NNs surprisingly obey... the ideal gas law ๐คฏ
Thermodynamics helps us to understand how train hyperparams shape final solutions!
๐งต๐1/8
Bayesian Methods Research Group retweeted
๐๐๐
1/ The original GFlowNets paper tried PPO for sampling, but it failed. We figured out why and fixed it. And now PPO beats all objectives on standard problems including molecular graph generation in large spaces.
Did you like our research on neural networks weights and loss landscapes? Be sure to check out the @weightsummetry #ICML2026 workshop co-organized by our alumni @KateLobacheva
3
743
โ ๏ธ New paper alert!
Excited to present CasTex (#WACV2026) ๐
Our text-to-texture method optimizes explicit PBR maps via SDS on cascaded pixel-space diffusion models, avoiding latent artifacts and producing relightable textures ready for production use.
Paper & Code โฌ๏ธ
thecrazymage.github.io/CasTeโฆ
557
Not a mirage but our new paper!
๐จ New paper alert! ๐จ
Our new paper on ArXiv: "MiAD: Mirage Atom Diffusion for De Novo Crystal Generation".
We unlock an ability to dynamically add or remove atoms during generation in diffusion models for better materials discovery.
๐ arxiv.org/abs/2511.14426
1/5
3
501
New paper! #NeurIPS2025
๐COSMOS is OUT! @NeurIPSconf 2025!
๐COSMOSย achieves up toย 2xย faster text generation compared to other diffusion models, utilizing up toย 8x compression in text representations for superior efficiency.
๐ย Paper:ย arxiv.org/pdf/2506.21170
๐ปย Code:ย github.com/MeshchaninovViachโฆ
(1/6)
1
498
Bayesian Methods Research Group retweeted
While frontier labs are announcing their new models, we also want to be part of this parade. So, weโre happy to announce gfnx โ a JAX-first library with environments and a single-file baseline implementation for GFlowNet research.
Bayesian Methods Research Group retweeted
1/ Can we efficiently learn the destruction process of diffusion samplers? Can we learn not just the drift, but also the variance for all transition kernels? โ We answer YES in our recent paper โAdaptive Destruction Processes for Diffusion Samplersโ (Oral at NeurIPS 2025 FPI Workshop).
Check out our new paper!
(1/n) The usual assumption in GFlowNet environments is acyclicity. Have you ever wondered if it can be relaxed? Does the existing GFlowNet theory translate to the non-acyclic case? Is efficient training possible?
We shed new light on these questions in our latest work! @icmlconf
3
500
Check out our new work!
๐จ New paper alert! ๐จ
Our new paper on ArXiv: "DreamBooth DPO: Controlled Optimization of Personalized Diffusion Models"
It addresses the core trade-off in personalized T2I: concept fidelity vs. prompt alignment, without any human-curated data
๐ arxiv.org/abs/2505.20975
1/5
2
393
Check out our new work!
๐จ New paper alert! ๐จ
Our new paper on ArXiv: "ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Models".
It tackles a key challenge in diffusion models: aligning with human preferences without collapsing diversity
๐ arxiv.org/abs/2505.22569
1/5
3
388
Bayesian Methods Research Group retweeted
๐จโ๐ผNeural Flow Diffusion Models at #NeurIPS2024 tomorrow! Discover how to build learnable noising processes for straight-line generative trajectories end-to-end and without simulations!๐คฏ
๐West Ballroom A-D #6809
โฐFri 13 Dec 4:30 pm โ 7:30 pm
๐neurips.cc/virtual/2024/postโฆ
๐ฅ Excited to share our new work on Neural Flow Diffusion Models โ a general, end-to-end, simulation-free framework that works with an arbitrary noising processes and even enables learning them!
๐: arxiv.org/abs/2404.12940
๐งต 1/11
Check out our new paper! To be presented at #NeurIPS2024 by @KateLobacheva this Friday (poster #2408 / Poster Session 5 East / 13 Dec 11 am โ 2 pm PST)
Starting training with a large learning rate benefits generalizationโbut why? In our new #NeurIPS2024 paper, we investigate its role in navigating the loss landscape and its effect on feature learning! 1/7
Paper: arxiv.org/abs/2410.22113
Poster: nips.cc/virtual/2024/poster/โฆ
3
433
We got 4 papers accepted to #NeurIPS2024!
1
4
520
๐ก๐ฒ๐๐ฟ๐ฎ๐น ๐๐น๐ผ๐ ๐๐ถ๐ณ๐ณ๐๐๐ถ๐ผ๐ป ๐ ๐ผ๐ฑ๐ฒ๐น๐: ๐๐ฒ๐ฎ๐ฟ๐ป๐ฎ๐ฏ๐น๐ฒ ๐๐ผ๐ฟ๐๐ฎ๐ฟ๐ฑ ๐ฃ๐ฟ๐ผ๐ฐ๐ฒ๐๐ ๐ณ๐ผ๐ฟ ๐๐บ๐ฝ๐ฟ๐ผ๐๐ฒ๐ฑ ๐๐ถ๐ณ๐ณ๐๐๐ถ๐ผ๐ป ๐ ๐ผ๐ฑ๐ฒ๐น๐น๐ถ๐ป๐ด
by Grigory Bartosh, Dmitry Vetrov, Christian A. Naesseth
arxiv.org/abs/2404.12940
๐๐ฎ๐ถ๐ฟ๐๐ฎ๐๐๐๐๐ก: ๐ฅ๐ฒ๐ฎ๐น๐ถ๐๐๐ถ๐ฐ ๐ฎ๐ป๐ฑ ๐ฅ๐ผ๐ฏ๐๐๐ ๐๐ฎ๐ถ๐ฟ ๐ง๐ฟ๐ฎ๐ป๐๐ณ๐ฒ๐ฟ ๐๐ถ๐๐ต ๐ฎ ๐๐ฎ๐๐ ๐๐ป๐ฐ๐ผ๐ฑ๐ฒ๐ฟ-๐๐ฎ๐๐ฒ๐ฑ ๐๐ฝ๐ฝ๐ฟ๐ผ๐ฎ๐ฐ๐ต
by Maxim Nikolaev, Mikhail Kuznetsov, Dmitry Vetrov, @ai_alanov
arxiv.org/abs/2404.01094
2
1,002
Bayesian Methods Research Group retweeted
Did you know that networks trained with different learning rates extract different features (and a different number of them!) from the data? Come by our poster at HiLD Workshop #ICML2024 tomorrow to discuss it with @irsadrtdinov!
Paper: openreview.net/forum?id=IID2โฆ
1/6

























