8 citations · 33 across the 38 of their papers we have counts for
41 papers
Fixed-point neural samplers on discrete spaces
Jiajun He, Denis Blessing, Mouyang Cheng +2
Sampling from discrete, unnormalized distributions without access to data is a challenging problem. Neural samplers offer a promising approach by training generative models from de…
Bigger Text Encoders Can Hurt CLIP Zero-Shot Performance
Samir Char, Carles Domingo-Enrich, Randall Balestriero
Contrastive Language-Image Pretraining (CLIP) is a building block of many machine learning applications. Scaling laws have guided resource allocation for large-scale training, yet…
JANUS: A Multi-modal Foundation Neural Sampler for Disordered Materials
Denis Blessing, Mouyang Cheng, Maximilian Schebek +4
Disordered materials are central to modern technologies, from high-performance alloys to quantum devices, yet understanding and designing them requires exploring an enormous space…
ATLAS: A Foundation Neural Sampler for Amorphous Materials
Mouyang Cheng, Denis Blessing, Botao Yu +4
Amorphous materials exhibit exceptional mechanical and functional properties, yet their rugged energy landscapes are notoriously difficult to sample. Below the glass-transition tem…
Free energy Estimation on Any State Space
Jiajun He, Zijing Ou, Francisco Vargas +4
Free energy estimation is a fundamental yet challenging problem, from physics to statistics. Classical approaches rely on thermodynamic transformations, ranging from direct estimat…
Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models
Andreas Bergmeister, Stefanie Jegelka, Nikolas Nüsken +2
Diffusion and flow-matching models scale because pretraining is supervised regression: a clean sample is noised analytically, and a model regresses against a closed-form target. RL…
A unified perspective on fine-tuning and sampling with diffusion and flow models
Carles Domingo-Enrich, Yuanqi Du, Michael S. Albergo
We study the problem of training diffusion and flow generative models to sample from target distributions defined by an exponential tilting of a base density; a formulation that su…
Rare Event Analysis via Stochastic Optimal Control
Yuanqi Du, Jiajun He, Dinghuai Zhang +2
Rare events such as conformational changes in biomolecules, phase transitions, and chemical reactions are central to the behavior of many physical systems, yet they are extremely d…
Adjoint Matching through the Lens of the Stochastic Maximum Principle in Optimal Control
Carles Domingo-Enrich, Jiequn Han
Reward fine-tuning of diffusion and flow models and sampling from tilted or Boltzmann distributions can both be formulated as stochastic optimal control (SOC) problems, where learn…
Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models
Samy Jelassi, Mujin Kwun, Rosie Zhao +5
Cross-entropy (CE) training provides dense and scalable supervision for language models, but it optimizes next-token prediction under teacher forcing rather than sequence-level beh…
Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
Noah Golowich, Fan Chen, Dhruv Rohatgi +4
Inference-time methods that aggregate and prune multiple samples have emerged as a powerful paradigm for steering large language models, yet we lack any principled understanding of…
Value Gradient Guidance for Flow Matching Alignment
Zhen Liu, Tim Z. Xiao, Carles Domingo-Enrich +2
While methods exist for aligning flow matching models--a popular and effective class of generative models--with human preferences, existing approaches fail to achieve both adaptati…
Test-time scaling of diffusions with flow maps
Amirmojtaba Sabour, Michael S. Albergo, Carles Domingo-Enrich +4
A common recipe to improve diffusion models at test-time so that samples score highly against a user-specified reward is to introduce the gradient of the reward into the dynamics o…
Rethinking Reasoning with MDLMs: Early Exits, Post-hoc Reasoning, and Beyond
Zachary Horvitz, Raghav Singhal, Hao Zou +4
The reasoning paradigm, where language models reason before answering, has enabled breakthroughs on tasks such as mathematical problem-solving. While current tooling for reasoning…
Any-Order Flexible Length Masked Diffusion
Jaeyeon Kim, Lee Cheuk-Kit, Carles Domingo-Enrich +5
Masked diffusion models (MDMs) have recently emerged as a promising alternative to autoregressive models over discrete domains. MDMs generate sequences in an any-order, parallel fa…
Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference
Denis Blessing, Julius Berner, Lorenz Richter +4
Solving stochastic optimal control problems with quadratic control costs can be viewed as approximating a target path space measure, e.g. via gradient-based optimization. In practi…
Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching
Aaron Havens, Benjamin Kurt Miller, Bing Yan +10
We introduce Adjoint Sampling, a highly scalable and efficient algorithm for learning diffusion processes that sample from unnormalized densities, or energy functions. It is the fi…
Conditioning Diffusions Using Malliavin Calculus
Jakiw Pidstrigach, Elizabeth Baker, Carles Domingo-Enrich +2
In generative modelling and stochastic optimal control, a central computational task is to modify a reference diffusion process to maximise a given terminal-time reward. Most exist…
Cheap Permutation Testing
Carles Domingo-Enrich, Raaz Dwivedi, Lester Mackey
Permutation tests are a popular choice for distinguishing distributions and testing independence, due to their exact, finite-sample control of false positives and their minimax opt…
A Taxonomy of Loss Functions for Stochastic Optimal Control
Carles Domingo-Enrich
Stochastic optimal control (SOC) aims to direct the behavior of noisy systems and has widespread applications in science, engineering, and artificial intelligence. In particular, r…
Towards deep learning sequence-structure co-generation for protein design
Chentong Wang, Sarah Alamdari, Carles Domingo-Enrich +2
Deep generative models that learn from the distribution of natural protein sequences and structures may enable the design of new proteins with valuable functions. While the majorit…
Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control
Carles Domingo-Enrich, Michal Drozdzal, Brian Karrer +1
Dynamical generative models that produce samples through an iterative process, such as Flow Matching and denoising diffusion models, have seen widespread use, but there have not be…
Neural Optimal Transport with Lagrangian Costs
Aram-Alexandre Pooladian, Carles Domingo-Enrich, Ricky T. Q. Chen +1
We investigate the optimal transport problem between probability measures when the underlying cost function is understood to satisfy a least action principle, also known as a Lagra…
Stochastic Optimal Control Matching
Carles Domingo-Enrich, Jiequn Han, Brandon Amos +2
Stochastic optimal control, which has the goal of driving the behavior of noisy systems, is broadly applicable in science, engineering and artificial intelligence. Our work introdu…