Publications and other work
Vignac*, Krawczuk*, Siraudin, Wang, Cevher, Frossard - *equal contribution
DiGress generates graphs by denoising in discrete space instead of lifting the problem into continuous space. The discrete formulation keeps node and edge types categorical the whole way through, which enables computing rich features and was the first graph diffusion paper to scale to the MOSES and Guacamol molecular benchmarks. Co-first author; cited 800+ times as of June 2026, about 140 of those flagged as highly influential. Citation counts are from Google Scholar, as of June 2026.
Latorre*, Krawczuk*, Dadi*, Pethick, Cevher
The inner step in standard adversarial training is not, in general, a descent direction on the robust loss because Danskin doesn’t apply to non-convex settings. So the loop is optimizing something other than what you wrote down, and you need to pick a safe descent direction (we propose a method based on norm minimization in the space spanned by directions).
Ramezani-Kebrya*, Antonakopoulos*, Krawczuk*, Deschenaux, Cevher
When using quantization for distributed training of GANs or multi-agent RL, the additional variance due to quantization can slow down convergence. In this paper we formalize this, show that extra-gradient type methods with adaptive quantization can maintain the optimal oracle complexity while decreasing communication overhead, and show this theory translates to practice on standard benchmarks.
with Patrick Kidger, Bruno Correia, and the Adaptyv team
At Adaptyv Bio we designed and ran an open competition for EGFR binders: about 159 participants submitted 1,800+ designs, and we put 601 of them through automated BLI to measure what actually bound. Hit-rates rose round over round as participants saw the previous round’s measurements and we wrote a few blog posts and a paper about it.
Filling gaps in trustworthy development of AI
Science 2021Avin, Belfield, Brundage, Krueger, Wang, Weller, Anderljung, Krawczuk, et al.
A short Science piece, summarizing the longer Brundage et al. report Toward Trustworthy AI Development on mechanisms that could increase trust of outside parties into AI systems.
Method for interfacing with hardware accelerators
US Patent 11,250,107Piveteau, Ioannou, Krawczuk, Le Gallo-Bourdeau, Sebastian, Eleftheriou
From the neuromorphic work: a method for interfacing software with ReRAM-based hardware accelerators.
GG-GAN: A Geometric Graph Generative Adversarial Network
preprint, ICLR 2021 submissionKrawczuk*, Abranches*, Loukas*, Cevher - *equal contribution
An earlier take on graph generation: a GAN built on permutation-aware geometric node embeddings, part of the same discrete-structure line of work later pushed further by DiGress.
A Computational Turn in Policy Process Studies: Coevolving Network Dynamics of Policy Change
Complexity 2022Stauffer, Mengesha, Seifert, Krawczuk, Fischer, Di Marzo Serugendo
Models policy change as coevolving network dynamics. A complexity-theoretic view of the policy process, on the governance/political-economy side of my work.
Optimization Theory, Economics and the Real World
Talk / essay - Assoziation EKrawczuk
A non-technical talk sketching a research plan at the intersection of optimization theory, economics, and political economy.
Proximal Point Imitation Learning
NeurIPS 2022A proximal-point treatment of imitation learning, on the optimization side of the work.
On zero-shot interpolation behaviour of denoising diffusion models - continuing the generative-modelling line.
Graph Generative Deep Learning Models with an Application to Circuit Topologies
PhD thesis, EPFL 2024Krawczuk
My doctoral thesis (EPFL, defended July 2024): graph generative deep-learning models, with an application to integrated-circuit topologies.