101 citations · 173 across the 27 of their papers we have counts for
29 papers
DSL-LLaDA: Scaling Continuous Denoising to 8B Masked Diffusion LMs
Longxuan Yu, Yunshu Wu, Yu Fu +5
Discrete Masked diffusion language models generate text by iterative parallel decoding, but few-step decoding suffers from a tradeoff between length and quality: with a fixed step…
Discrete Stochastic Localization for Non-autoregressive Generation
Yunshu Wu, Jiayi Cheng, Longxuan Yu +4
Continuous diffusion is a natural framework for non-autoregressive generation but has generally lagged behind masked discrete diffusion models (MDMs) on discrete sequence generatio…
Scalable Spatio-Temporal SE(3) Diffusion for Long-Horizon Protein Dynamics
Nima Shoghi, Yuxuan Liu, Yuning Shen +3
Molecular dynamics (MD) simulations remain the gold standard for studying protein dynamics, but their computational cost limits access to biologically relevant timescales. Recent g…
Discrete Stochastic Localization for Non-autoregressive Generation
Yunshu Wu, Jiayi Cheng, Longxuan Yu +4
Continuous diffusion is a natural framework for non-autoregressive generation but has generally lagged behind masked discrete diffusion models (MDMs) on discrete sequence generatio…
Generation Order and Parallel Decoding in Masked Diffusion Models: An Information-Theoretic Perspective
Shaorong Zhang, Longxuan Yu, Rob Brekelmans +3
Masked Diffusion Models (MDMs) significantly accelerate inference by trading off sequential determinism. However, the theoretical mechanisms governing generation order and the risk…
Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic Inference
Stephen Zhao, Aidan Li, Rob Brekelmans +1
Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given…
Local MAP Sampling for Diffusion Models
Shaorong Zhang, Rob Brekelmans, Greg Ver Steeg
Diffusion Posterior Sampling (DPS) provides a principled Bayesian approach to inverse problems by sampling from . While posterior sampling is valuable for capturing…
Measurement-Aligned Sampling for Inverse Problem
Shaorong Zhang, Rob Brekelmans, Yunshu Wu +1
Diffusion models provide a powerful way to incorporate complex prior information for solving inverse problems. However, existing methods struggle to correctly incorporate guidance…
Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts
Marta Skreta, Tara Akhound-Sadegh, Viktor Ohanesian +6
While score-based generative models are the model of choice across diverse domains, there are limited tools available for controlling inference-time behavior in a principled manner…
Generalized Flow Matching for Transition Dynamics Modeling
Haibo Wang, Yuxuan Qiu, Yanze Wang +2
Simulating transition dynamics between metastable states is a fundamental challenge in dynamical systems and stochastic processes with wide real-world applications in understanding…
Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling
Yuanqi Du, Michael Plainer, Rob Brekelmans +5
Rare event sampling in dynamical systems is a fundamental problem arising in the natural sciences, which poses significant computational challenges due to an exponentially large sp…
Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo
Stephen Zhao, Rob Brekelmans, Alireza Makhzani +1
Numerous capability and safety techniques of Large Language Models (LLMs), including RLHF, automated red-teaming, prompt engineering, and infilling, can be cast as sampling from an…
A Computational Framework for Solving Wasserstein Lagrangian Flows
Kirill Neklyudov, Rob Brekelmans, Alexander Tong +3
The dynamical formulation of the optimal transport can be extended through various choices of the underlying geometry (kinetic energy), and the regularization of density paths (pot…
Improving Mutual Information Estimation with Annealed and Energy-Based Bounds
Rob Brekelmans, Sicong Huang, Marzyeh Ghassemi +3
Mutual information (MI) is a fundamental quantity in information theory and machine learning. However, direct estimation of MI is intractable, even if the true joint probability de…
Information-Theoretic Diffusion
Xianghao Kong, Rob Brekelmans, Greg Ver Steeg
Denoising diffusion models have spurred significant gains in density modeling and image generation, precipitating an industrial revolution in text-guided AI art generation. We intr…
Action Matching: Learning Stochastic Dynamics from Samples
Kirill Neklyudov, Rob Brekelmans, Daniel Severo +1
Learning the continuous dynamics of a system from snapshots of its temporal marginals is a problem which appears throughout natural sciences and machine learning, including in quan…
Variational Representations of Annealing Paths: Bregman Information under Monotonic Embedding
Rob Brekelmans, Frank Nielsen
Markov Chain Monte Carlo methods for sampling from complex distributions and estimating normalization constants often simulate samples from a sequence of intermediate distributions…
Your Policy Regularizer is Secretly an Adversary
Rob Brekelmans, Tim Genewein, Jordi Grau-Moya +4
Policy regularization methods such as maximum entropy regularization are widely used in reinforcement learning to improve the robustness of a learned policy. In this paper, we show…
Model-Free Risk-Sensitive Reinforcement Learning
Grégoire Delétang, Jordi Grau-Moya, Markus Kunesch +4
We extend temporal-difference (TD) learning in order to obtain risk-sensitive, model-free reinforcement learning algorithms. This extension can be regarded as modification of the R…
q-Paths: Generalizing the Geometric Annealing Path using Power Means
Vaden Masrani, Rob Brekelmans, Thang Bui +4
Many common machine learning methods involve the geometric annealing path, a sequence of intermediate densities between two distributions of interest constructed using the geometri…
Likelihood Ratio Exponential Families
Rob Brekelmans, Frank Nielsen, Alireza Makhzani +2
The exponential family is well known in machine learning and statistical physics as the maximum entropy distribution subject to a set of observed constraints, while the geometric m…
Annealed Importance Sampling with q-Paths
Rob Brekelmans, Vaden Masrani, Thang Bui +4
Annealed importance sampling (AIS) is the gold standard for estimating partition functions or marginal likelihoods, corresponding to importance sampling over a path of distribution…
Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective
Vu Nguyen, Vaden Masrani, Rob Brekelmans +2
Achieving the full promise of the Thermodynamic Variational Objective (TVO), a recently proposed variational lower bound on the log evidence involving a one-dimensional Riemann int…
All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference
Rob Brekelmans, Vaden Masrani, Frank Wood +2
The recently proposed Thermodynamic Variational Objective (TVO) leverages thermodynamic integration to provide a family of variational inference objectives, which both tighten and…