Preprints & Publications Preprints Fixed-point neural samplers on discrete spaces Carles Domingo-Enrich . Oct. 2026Bigger Text Encoders Can Hurt CLIP Zero-Shot Performance Carles Domingo-Enrich , Randall Balestriero. Sept. 2026JANUS: A Multi-modal Foundation Neural Sampler for Disordered Materials Carles Domingo-Enrich †, Yuanqi Du†. Aug. 2026ATLAS: A Foundation Neural Sampler for Amorphous Materials Carles Domingo-Enrich †, Yuanqi Du†. Jul. 2026Rare Event Analysis via Stochastic Optimal Control Carles Domingo-Enrich . April 2026Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models Carles Domingo-Enrich *. March 2026The Dayhoff Atlas: scaling sequence diversity for improved protein generation Carles Domingo-Enrich , Chentong Wang, Suyue Lyu, Nicolo Fusi, Neil Tenenholtz, Ava P. Amini. Jul. 2025Publications Free energy Estimation on Any State Space Carles Domingo-Enrich , Yuanqi Du. NeurIPS 2026Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models Carles Domingo-Enrich *, Jakiw Pidstrigach* (*Senior authors). NeurIPS 2026Adjoint Matching through the Lens of the Stochastic Maximum Principle in Optimal Control Carles Domingo-Enrich , Jiequn Han. TMLR 2026Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference Carles Domingo-Enrich , Dylan J. Foster, Akshay Krishnamurthy. NeurIPS 2026Test-time scaling of diffusions with flow maps Carles Domingo-Enrich *, Nicholas M. Boffi, Sanja Fidler, Karsten Kreis, Eric Vanden-Eijnden (*Equal contribution). NeurIPS 2026Rethinking Reasoning with MDLMs: Early Exits, Post-hoc Reasoning, and Beyond Carles Domingo-Enrich , Zhou Yu, Rajesh Ranganath, Kathleen McKeown. COLM 2026Cheap Permutation Testing Carles Domingo-Enrich , Raaz Dwivedi, Lester Mackey. Annals of Statistics (to appear)Any-order flexible length masked diffusion Carles Domingo-Enrich , Yilun Du, Sham Kakade, Timothy Ngotiaoco, Sitan Chen, Michael Albergo (*Equal contribution). ICLR 2026.Trust region constrained measure transport in path space for stochastic optimal control and inference Carles Domingo-Enrich *, Yuanqi Du, Arash Vahdat, Gerhard Neumann (*Equal contribution). NeurIPS 2025, Spotlight .Value Gradient Guidance for Flow Matching Alignment Carles Domingo-Enrich , Weiyang Liu, Dinghuai Zhang. NeurIPS 2025Adjoint sampling: highly scalable diffusion samplers via adjoint matching Carles Domingo-Enrich , Anuroop Sriram, Brandon Wood, Daniel Levine, Bin Hu, Brandon Amos, Brian Karrer, Xiang Fu, Guan-Horng Liu, Ricky T. Q. Chen. ICML 2025Conditioning diffusions using Malliavin calculus Carles Domingo-Enrich , George Deligiannidis, Nikolas Nüsken. ICML 2025Adjoint matching: fine-tuning flow and diffusion generative models with memoryless stochastic optimal control Carles Domingo-Enrich , Michal Drozdzal, Brian Karrer, Ricky T. Q. Chen. ICLR 2025, Spotlight . Code here: https://github.com/microsoft/soc-fine-tuning-sd Towards deep learning sequence-structure co-generation for protein design Carles Domingo-Enrich , Ava Amini, Kevin K. Yang. Current Opinion in Structural Biology, 2025Stochastic optimal control matching Carles Domingo-Enrich , Jiequn Han, Brandon Amos, Joan Bruna, Ricky T. Q. Chen. NeurIPS 2024Neural optimal transport with Lagrangian costs Carles Domingo-Enrich , Ricky T. Q. Chen, Brandon Amos. UAI 2024An explicit expansion of the Kullback-Leibler divergence along its Fisher-Rao gradient flow Carles Domingo-Enrich , Aram-Alexandre Pooladian. TMLR 2023Multisample Flow Matching: straightening flows with minibatch couplings Carles Domingo-Enrich *, Brandon Amos, Yaron Lipman, Ricky T. Q. Chen (*Equal contribution). ICML 2023Compress Then Test: powerful kernel testing in near-linear time Carles Domingo-Enrich , Raaz Dwivedi, Lester Mackey. AISTATS 2023Learning with stochastic orders Carles Domingo-Enrich , Yair Schiff, Youssef Mroueh. ICLR 2023, Spotlight Depth and feature learning are provably beneficial for neural network discriminators Carles Domingo-Enrich . COLT 2022Tighter sparse approximation bounds for ReLU neural networks Carles Domingo-Enrich , Youssef Mroueh. ICLR 2022, Spotlight Separation results between fixed-kernel and feature-learning probability metrics Carles Domingo-Enrich , Youssef Mroueh. NeurIPS 2021, Oral On energy-based models with overparametrized shallow neural networks Carles Domingo-Enrich , Alberto Bietti, Eric Vanden-Eijnden, Joan Bruna. ICML 2021, Long talk Average-case acceleration for bilinear games and normal matrices Carles Domingo-Enrich , Damien Scieur, Fabian Pedregosa. ICLR 2021A mean-field analysis of two-player zero-sum games Carles Domingo-Enrich , Samy Jelassi, Arthur Mensch, Grant M. Rotskoff, Joan Bruna. NeurIPS 2020Extra-gradient with player sampling for faster Nash equilibrium finding Carles Domingo-Enrich *, Damien Scieur, Arthur Mensch, Joan Bruna (*Equal contribution). ICML 2020Outsourcing scalar products and matrix products on privacy-protected unencrypted data stored in untrusted clouds Carles Domingo-Enrich . Information Sciences, Vol. 436, pp. 320-342, Apr 2018Technical reports A unified perspective on fine-tuning and sampling with diffusion and flow models Carles Domingo-Enrich , Yuanqi Du, Michael S. Albergo. Apr. 2026A taxonomy of loss functions for stochastic optimal control Carles Domingo-Enrich . Oct. 2024Length generalization in arithmetic transformers Carles Domingo-Enrich , Yuhuai Wu, Yuanzhi Li, François Charton. Jun. 2023Open problem: learning with variational objectives on measures Carles Domingo-Enrich . Jun. 2023Computing the variance of shuffling stochastic gradient algorithms via power spectral density analysis Carles Domingo-Enrich . Jun. 2022Auditing differential privacy in high dimensions with the kernel quantum Rényi divergence Carles Domingo-Enrich , Youssef Mroueh. May 2022Simultaneous transport evolution for minimax equilibria on measures Carles Domingo-Enrich , Joan Bruna. Feb. 2022Dual training of energy-based models with overparametrized shallow neural networks Carles Domingo-Enrich , Alberto Bietti, Marylou Gabrié, Joan Bruna, Eric Vanden-Eijnden. Jul. 2021
