Timofei Gritsaev

Got asked in a review for my ICML paper whether "there are realistic tasks where one needs to sample from a probability distribution given by its unnormalized density" (rephrased for anonymity). Are we cooked?

LOTs of discourse lately about the correctness of the KL-regularization term used in RLVR fine-tuning of LLMs. Which estimator to use? Whether to add it to the reward or loss? What’s even the difference? 🤔 In our new preprint, we evaluate these choices empirically. 🧵 1/n

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.

Happy to share that our work on diffusion samplers was accepted as Oral at #NeurIPS2025 FPI Workshop! 🎉 We show how setting both generation and destruction transition kernels as Gaussians with learnable means and variances produces accurate samplers even at very few steps.

7/ Huge thanks to my amazing co-authors: @nvimorozov,@ktamogashev, @dtiapkin, @svsamsonov, Alexey Naumov, Dmitry Vetrov, and @FelineAutomaton! The full version: arxiv.org/abs/2506.01541

6/ But it’s not limited to small-scale problems. We successfully use these methods to improve outsourced sampling: Bayesian posterior inference in latent spaces of generative models.

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).

@dtiapkin Congratulations Danya!

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.

(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

6/ Read the paper here: openreview.net/forum?id=Xj66f…. See you in Singapore! Huge thanks to my co-authors @nvimorozov, @svsamsonov, and @dtiapkin!

5/ The results? Faster convergence across many standard GFlowNet approaches—including soft RL-based ones! We also faced the complexity hypothesis: the less structured the environment, the more crucial backward policy optimization becomes.

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.

@Pavel_Izmailov @nyuniversity Is it reasonable to apply, if I am finishing bachelor degree this year?

📢 I am recruiting Ph.D. students for my new lab at @nyuniversity! Please apply, if you want to work on understanding deep learning and large models, and do a Ph.D. in the most exciting city on earth. Details on my website: izmailovpavel.github.io. Please spread the word!