7 papers · 1 filter
Synthesizable Molecular Generation via Soft-constrained GFlowNets with Rich Chemical Priors
Hyeonah Kim, Minsu Kim, Celine Roget +5
The application of generative models for experimental drug discovery campaigns is severely limited by the difficulty of designing molecules de novo that can be synthesized in pract…
Offline Model-Based Optimization: Comprehensive Review
Minsu Kim, Jiayao Gu, Ye Yuan +4
Offline optimization is a fundamental challenge in science and engineering, where the goal is to optimize black-box functions using only offline datasets. This setting is particula…
Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training
Brian Bartoldson, Siddarth Venkatraman, James Diffenderfer +7
Reinforcement learning (RL) is a critical component of large language model (LLM) post-training. However, on-policy algorithms used for post-training are not naturally robust to a…
Adaptive Inference-Time Scaling via Cyclic Diffusion Search
Gyubin Lee, Truong Nhat Nguyen Bao, Jaesik Yoon +4
Diffusion models have demonstrated strong generative capabilities across domains ranging from image synthesis to complex reasoning tasks. However, most inference-time scaling metho…
Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models
Siddarth Venkatraman, Mohsin Hasan, Minsu Kim +5
Any well-behaved generative model over a variable can be expressed as a deterministic transformation of an exogenous ('outsourced') Gaussian noise variable $\mathbf{z}…
Solving Bayesian inverse problems with diffusion priors and off-policy RL
Luca Scimeca, Siddarth Venkatraman, Moksh Jain +14
This paper presents a practical application of Relative Trajectory Balance (RTB), a recently introduced off-policy reinforcement learning (RL) objective that can asymptotically sol…