Kusha Sareen

Energy Loss Functions for Physical Systems

Sékou-Oumar Kaba

Kusha Sareen

Daniel Levy

Siamak Ravanbakhsh

Effectively leveraging prior knowledge of a system's physics is crucial for applications of machine learning to scientific domains. Previous… (see more) approaches mostly focused on incorporating physical insights at the architectural level. In this paper, we propose a framework to leverage physical information directly into the loss function for prediction and generative modeling tasks on systems like molecules and spins. We derive energy loss functions assuming that each data sample is in thermal equilibrium with respect to an approximate energy landscape. By using the reverse KL divergence with a Boltzmann distribution around the data, we obtain the loss as an energy difference between the data and the model predictions. This perspective also recasts traditional objectives like MSE as energy-based, but with a physically meaningless energy. In contrast, our formulation yields physically grounded loss functions with gradients that better align with valid configurations, while being architecture-agnostic and computationally efficient. The energy loss functions also inherently respect physical symmetries. We demonstrate our approach on molecular generation and spin ground-state prediction and report significant improvements over baselines.

2025-09-17

NeurIPS.cc/2025/Conference (poster)

Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers

Morgane M Moss

2025-07-07

colmweb.org/COLM/2025/Conference (accepted)

Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models

Adapting a pretrained diffusion model to new objectives at inference time remains an open problem in generative modeling. Existing steering … (see more)methods suffer from inaccurate value estimation, especially at high noise levels, which biases guidance. Moreover, information from past runs is not reused to improve sample quality, resulting in inefficient use of compute. Inspired by the success of Monte Carlo Tree Search, we address these limitations by casting inference-time alignment as a search problem that reuses past computations. We introduce a tree-based approach that samples from the reward-aligned target density by propagating terminal rewards back through the diffusion chain and iteratively refining value estimates with each additional generation. Our proposed method, Diffusion Tree Sampling (DTS), produces asymptotically exact samples from the target distribution in the limit of infinite rollouts, and its greedy variant, Diffusion Tree Search (DTS

2025-06-25

ArXiv (preprint)

Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models

Adapting a pretrained diffusion model to new objectives at inference time remains an open problem in generative modeling. Existing steering … (see more)methods suffer from inaccurate value estimation, especially at high noise levels, which biases guidance. Moreover, information from past runs is not reused to improve sample quality, resulting in inefficient use of compute. Inspired by the success of Monte Carlo Tree Search, we address these limitations by casting inference-time alignment as a search problem that reuses past computations. We introduce a tree-based approach that samples from the reward-aligned target density by propagating terminal rewards back through the diffusion chain and iteratively refining value estimates with each additional generation. Our proposed method, Diffusion Tree Sampling (DTS), produces asymptotically exact samples from the target distribution in the limit of infinite rollouts, and its greedy variant, Diffusion Tree Search (DTS

2025-06-25

ArXiv (preprint)

Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models

Adapting a pretrained diffusion model to new objectives at inference time remains an open problem in generative modeling. Existing steering … (see more)methods suffer from inaccurate value estimation, especially at high noise levels, which biases guidance. Moreover, information from past runs is not reused to improve sample quality, resulting in inefficient use of compute. Inspired by the success of Monte Carlo Tree Search, we address these limitations by casting inference-time alignment as a search problem that reuses past computations. We introduce a tree-based approach that samples from the reward-aligned target density by propagating terminal rewards back through the diffusion chain and iteratively refining value estimates with each additional generation. Our proposed method, Diffusion Tree Sampling (DTS), produces asymptotically exact samples from the target distribution in the limit of infinite rollouts, and its greedy variant, Diffusion Tree Search (DTS

2025-06-10

ICML.cc/2025/Workshop/PUT (poster)

Diffusion Tree Sampling: Scalable inference‑time alignment of diffusion models

Adapting a pretrained diffusion model to new objectives at inference time remains an open problem in generative modeling. Existing steering … (see more)methods suffer from inaccurate value estimation, especially at high noise levels, which biases guidance. Moreover, information from past runs is not reused to improve sample quality, leading to inefficient use of compute. Inspired by the success of Monte Carlo Tree Search, we address these limitations by casting inference-time alignment as a search problem that reuses past computations. We introduce a tree-based approach that _samples_ from the reward-aligned target density by propagating terminal rewards back through the diffusion chain and iteratively refining value estimates with each additional generation. Our proposed method, Diffusion Tree Sampling (DTS), produces asymptotically exact samples from the target distribution in the limit of infinite rollouts, and its greedy variant Diffusion Tree Search (DTS*) performs a robust search for high reward samples. On MNIST and CIFAR-10 class-conditional generation, DTS matches the FID of the best-performing baseline with up to

2025-06-10

ICML.cc/2025/Workshop/PUT (poster)

Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers

Morgane M Moss

2025-05-07

ArXiv (preprint)

Symmetry-Aware Generative Modeling through Learned Canonicalization

Kusha Sareen

Daniel Levy

Arnab Kumar Mondal

Sékou-Oumar Kaba

Tara Akhound-Sadegh

Siamak Ravanbakhsh

Generative modeling of symmetric densities has a range of applications in AI for science, from drug discovery to physics simulations. The ex… (see more)isting generative modeling paradigm for invariant densities combines an invariant prior with an equivariant generative process. However, we observe that this technique is not necessary and has several drawbacks resulting from the limitations of equivariant networks. Instead, we propose to model a learned slice of the density so that only one representative element per orbit is learned. To accomplish this, we learn a group-equivariant canonicalization network that maps training samples to a canonical pose and train a non-equivariant generative model over these canonicalized samples. We implement this idea in the context of diffusion models. Our preliminary experimental results on molecular modeling are promising, demonstrating improved sample quality and faster inference time.

2025-01-14

ArXiv (preprint)

Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models

2025-01-01

arXiv.org (preprint)

Symmetry-Aware Generative Modeling through Learned Canonicalization

Kusha Sareen

Daniel Levy

Arnab Kumar Mondal

Sékou-Oumar Kaba

Tara Akhound-Sadegh

Siamak Ravanbakhsh

Generative modeling of symmetric densities has a range of applications in AI for science, from drug discovery to physics simulations. The ex… (see more)isting generative modeling paradigm for invariant densities combines an invariant prior with an equivariant generative process. However, we observe that this technique is not necessary and has several drawbacks resulting from the limitations of equivariant networks. Instead, we propose to model a learned slice of the density so that only one representative element per orbit is learned. To accomplish this, we learn a group-equivariant canonicalization network that maps training samples to a canonical pose and train a non-equivariant generative model over these canonicalized samples. We implement this idea in the context of diffusion models. Our preliminary experimental results on molecular modeling are promising, demonstrating improved sample quality and faster inference time.

2024-10-23

NeurIPS.cc/2024/Workshop/NeurReps (poster)