activity
20242026
collaborators

6 papers

cs.LG2026

Symmetry-Aware Generative Modeling through Learned Canonicalization

Kusha Sareen, Daniel Levy, Arnab Kumar Mondal +3

Generative modeling of symmetric densities has a range of applications in AI for science, from drug discovery to physics simulations. The existing generative modeling paradigm for…

cs.LG2025

FALCON: Few-step Accurate Likelihoods for Continuous Flows

Danyal Rehman, Tara Akhound-Sadegh, Artem Gazizov +2

Scalable sampling of molecular states in thermodynamic equilibrium is a long-standing challenge in statistical physics. Boltzmann Generators tackle this problem by pairing a genera…

cs.LG2025

Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities

Tara Akhound-Sadegh, Jungyoon Lee, Avishek Joey Bose +7

Sampling efficiently from a target unnormalized probability density remains a core challenge, with relevance across countless high-impact scientific applications. A promising appro…

cs.LG2025

Sampling from Energy-based Policies using Diffusion

Vineet Jain, Tara Akhound-Sadegh, Siamak Ravanbakhsh

Energy-based policies offer a flexible framework for modeling complex, multimodal behaviors in reinforcement learning (RL). In maximum entropy RL, the optimal policy is a Boltzmann…

cs.LG2025

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…

cs.LG2024

Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generation

Guillaume Huguet, James Vuckovic, Kilian Fatras +9

Proteins are essential for almost all biological processes and derive their diverse functions from complex 3D structures, which are in turn determined by their amino acid sequences…