Daniil Tiapkin retweeted
Excited to announce that our new book Reinforcement Learning Foundations is available for preorder!
W/ @shiemannor and @YishayMansour
30% discount and free shipping till July 21
Discount code 148294
cambridge.org/il/universityp…
Daniil Tiapkin retweeted
Meet DiffusionGemma!
An experimental open model that explores a fast approach to text generation, released under an Apache 2.0 license.
Moving beyond sequential, token-by-token processes to generate entire blocks of text simultaneously. Here’s what’s new with DiffusionGemma: 👇
Daniil Tiapkin retweeted
Happy to share our recent preprint:
Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation
Takeaways:
- standard implementations of uniform diffusion do not learn a denoiser, but rather a
"leave-one-out" denoiser
- uniform diffusion and masked diffusion are two sides of the same coin
paper: arxiv.org/abs/2605.22765
code: github.com/samsongourevitch/… (we release 9 models trained on owt)
with @samsongvch @dario_sha @umutsimsekli @EricMoulines @ericxing
@AlainDurmus
A short thread on our findings:
(1/5)
Daniil Tiapkin retweeted
🚀COSMOS is OUT! @NeurIPSconf 2025!
📈COSMOS achieves up to 2x faster text generation compared to other diffusion models, utilizing up to 8x compression in text representations for superior efficiency.
📄 Paper: arxiv.org/pdf/2506.21170
💻 Code: github.com/MeshchaninovViach…
(1/6)
While frontier labs are announcing their new models, we also want to be part of this parade. So, we’re happy to announce gfnx – a JAX-first library with environments and a single-file baseline implementation for GFlowNet research.
Environments, reward functions, metrics, and single-file implementations – everything you need to achieve up to 80× single-seed speedups for combinatorial object generation, from bit sequences and Ising models to phylogenetic trees.
2
7
333
Technical report: arxiv.org/abs/2511.16592
GitHub: github.com/d-tiapkin/gfnx
Docs: gfnx.readthedocs.io/en/lates…
Huge thanks to @agarkov_as @nvimorozov @ian_maksimov @ashtsyganov @gritsaev @svsamsonov!
Daniil Tiapkin 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? – We answer YES in our recent paper “Adaptive Destruction Processes for Diffusion Samplers” (Oral at NeurIPS 2025 FPI Workshop).
The speedrun is over: I defended my PhD this week and became a doctor in applied mathematics (unofficially: in reinforcement learning)!
Huge thanks to my supervisors (Eric & Gilles), collaborators, and friends for all the support.
If you're at #ICML2025, come say hi and learn about teacher hacking in distillation. See you at poster E-2706!
Daniil Tiapkin retweeted
(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
I'll be at #ICLR2025 this week - let's chat about RL, sampling and so on!
Excited for @gritsaev to present our work on backward policy optimization for GFlowNets (arxiv.org/abs/2410.15474, my first work as advisor!) on Sat morning, April 26, poster 454. Come to say hi to us!
Daniil Tiapkin retweeted
1/ GFlowNets are known for training a forward policy to generate complex objects step by step. However, an equally important piece specific to the GFlowNet paradigm is a backward policy, which undoes these steps and plays a crucial role in training.
1/ If you’re familiar with RLHF, you likely heard of reward hacking —where over-optimizing the imperfect reward model leads to unintended behaviors. But what about teacher hacking in knowledge distillation: can the teacher be hacked, like rewards in RLHF?
5/ Our suggestions are the following:
- Use online generations during distillation;
- Train on more diverse prompt datasets;
- Expand the dataset with multiple completions per prompt.
2
5
452
6/ Our paper is out: arxiv.org/abs/2502.02671. This work was the result of my internship at @GoogleDeepMind—huge thanks to the team: Daniele Calandriello, @johanferret, @sarah_perrin_, @nino_vieillard, @ramealexandre, @mblondel_ml!



















