Paper-Conference

Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities
Sampling efficiently from a target unnormalized probability density remains a core challenge, with relevance across countless …
Tara Akhound-Sadegh*, Jungyoon Lee*, Avishek Joey Bose, Valentin De Bortoli, Arnaud Doucet, Michael M. Bronstein, Dominique Beaini, Siamak Ravanbakhsh, Kirill Neklyudov*, Alex Tong*
PDF Cite Code
Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities
Amortized Sampling with Transferable Normalizing Flows
Efficient equilibrium sampling of molecular conformations remains a core challenge in computational chemistry and statistical …
Charlie B. Tan*, Majdi Hassan*, Leon Klein, Saifuddin Syed, Dominique Beaini, Michael M. Bronstein, Alex Tong*, Kirill Neklyudov*
PDF Cite Code Data
Curly Flow Matching for Learning Non-gradient Field Dynamics
Modeling the transport dynamics of natural processes from population-level observations is a ubiquitous problem in the natural …
Katarina Petrović, Lazar Atanackovic, Viggo Moro, Kacper Kapuśniak, İsmail İlkan Ceylan, Michael Bronstein, Avishek Joey Bose*, Alex Tong*
PDF Cite Code
Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts
While score-based generative models are the model of choice across diverse domains, there are limited tools available for controlling …
Marta Skreta*, Tara Akhound-Sadegh*, Viktor Ohanesian*, Roberto Bondesan, Alán Aspuru-Guzik, Arnaud Doucet, Rob Brekelmans, Alex Tong*, Kirill Neklyudov*
PDF Cite Code arXiv
Scalable Equilibrium Sampling with Sequential Boltzmann Generators
Scalable sampling of molecular states in thermodynamic equilibrium is a long-standing challenge in statistical physics. Boltzmann …
Charlie B. Tan*, Avishek Joey Bose*, Chen Lin, Leon Klein, Michael M. Bronstein, Alex Tong
PDF Cite Code
Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction
Generative modeling of discrete data underlies important applications spanning text-based agents like ChatGPT to the design of the very …
Jarrid Rector-Brooks, Mohsin Hasan, Zhangzhi Peng, Zachary Quinn, Chenghao Liu, Sarthak Mittal, Nouha Dziri, Michael Bronstein, Yoshua Bengio, Pranam Chatterjee, Alex Tong*, Avishek Joey Bose*
Cite arXiv
Generating Multi-Modal and Multi-Attribute Single-Cell Counts with CFGen
Alessandro Palma, Till Richter, Hanyi Zhang, Manuel Lubetzki, Alex Tong, Andrea Dittadi, Fabian Theis
Cite arXiv
Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold
Numerous biological and physical processes can be modeled as systems of interacting entities evolving continuously over time, e.g. the …
Lazar Atanackovic*, Xi Zhang*, Brandon Amos, Mathieu Blanchette, Leo J. Lee, Yoshua Bengio, Alex Tong, Kirill Neklyudov
Cite arXiv
The Superposition of Diffusion Models Using the Itô Density Estimator
Marta Skreta, Lazar Atanackovic, Avishek Joey Bose, Alex Tong, Kirill Neklyudov
PDF Cite arXiv
Trajectory Flow Matching with Applications to Clinical Time Series Modeling
Xi Zhang*, Yuan Pu*, Yuki Kawamura, Andrew Loza, Yoshua Bengio, Dennis L. Shung*, Alex Tong*
PDF Cite Code