10 papers
Process-Verified Reinforcement Learning for Theorem Proving via Lean
Minsu Kim, Se-Young Yun
While reinforcement learning from verifiable rewards (RLVR) typically has relied on a single binary verification signal, symbolic proof assistants in formal reasoning offer rich, f…
Generative Recursive Reasoning
Junyeob Baek, Mingyu Jo, Minsu Kim +3
How should future neural reasoning systems implement extended computation? Recursive Reasoning Models (RRMs) offer a promising alternative to autoregressive sequence extension by p…
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…
Latent Veracity Inference for Identifying Errors in Stepwise Reasoning
Minsu Kim, Jean-Pierre Falet, Oliver E. Richardson +5
Chain-of-Thought (CoT) reasoning has advanced the capabilities and transparency of language models (LMs); however, reasoning chains can contain inaccurate statements that reduce pe…
Adaptive teachers for amortized samplers
Minsu Kim, Sanghyeok Choi, Taeyoung Yun +7
Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnormalized density where exact sampling is in…
Pessimistic Backward Policy for GFlowNets
Hyosoon Jang, Yunhui Jang, Minsu Kim +2
This paper studies Generative Flow Networks (GFlowNets), which learn to sample objects proportionally to a given reward function through the trajectory of state transitions. In thi…
Improved off-policy training of diffusion samplers
Marcin Sendera, Minsu Kim, Sarthak Mittal +6
We study the problem of training diffusion models to sample from a distribution with a given unnormalized density or energy function. We benchmark several diffusion-structured infe…
Learning Energy Decompositions for Partial Inference of GFlowNets
Hyosoon Jang, Minsu Kim, Sungsoo Ahn
This paper studies generative flow networks (GFlowNets) to sample objects from the Boltzmann energy distribution via a sequence of actions. In particular, we focus on improving GFl…
Learning to Scale Logits for Temperature-Conditional GFlowNets
Minsu Kim, Joohwan Ko, Taeyoung Yun +6
GFlowNets are probabilistic models that sequentially generate compositional structures through a stochastic policy. Among GFlowNets, temperature-conditional GFlowNets can introduce…
Local Search GFlowNets
Minsu Kim, Taeyoung Yun, Emmanuel Bengio +4
Generative Flow Networks (GFlowNets) are amortized sampling methods that learn a distribution over discrete objects proportional to their rewards. GFlowNets exhibit a remarkable ab…