activity
20242026
collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2026

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2024

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…