6 papers
INDIBATOR: Diverse and Fact-Grounded Individuality for Multi-Agent Debate in Molecular Discovery
Yunhui Jang, Seonghyun Park, Jaehyung Kim +1
Multi-agent systems have emerged as a powerful paradigm for automating scientific discovery. To differentiate agent behavior in the multi-agent system, current frameworks typically…
Riemannian MeanFlow
Dongyeop Woo, Marta Skreta, Seonghyun Park +2
Diffusion and flow models have become the dominant paradigm for generative modeling on Riemannian manifolds, with successful applications in protein backbone generation and DNA seq…
Learning Collective Variables from BioEmu with Time-Lagged Generation
Seonghyun Park, Kiyoung Seong, Soojung Yang +2
Molecular dynamics is crucial for understanding molecular systems but its applicability is often limited by the vast timescales of rare events like protein folding. Enhanced sampli…
Energy-based generator matching: A neural sampler for general state space
Dongyeop Woo, Minsu Kim, Minkyu Kim +2
We propose Energy-based generator matching (EGM), a modality-agnostic approach to train generative models from energy functions in the absence of data. Extending the recently propo…
On scalable and efficient training of diffusion samplers
Minkyu Kim, Kiyoung Seong, Dongyeop Woo +2
We address the challenge of training diffusion models to sample from unnormalized energy distributions in the absence of data, the so-called diffusion samplers. Although these appr…
Iterated Energy-based Flow Matching for Sampling from Boltzmann Densities
Dongyeop Woo, Sungsoo Ahn
In this work, we consider the problem of training a generator from evaluations of energy functions or unnormalized densities. This is a fundamental problem in probabilistic inferen…