World models, game simulators, and long-take video creation require coherent scene evolution and sustained dynamics over extended durations. Autoregressive (AR) video diffusion provides a natural framework for long-horizon generation, yet extended rollouts often become near-static or lose visual quality. We hypothesize...
Byoungwoo Park, Jaemoo Choi, Juho Lee et al.· 0 citations
Large Language Model (LLM) agents are increasingly deployed under structured generation, where grammar constraints enforce output format at inference time. Whereas existing compression methods target unconstrained generation, we first identify a fundamental mismatch: under structured generation, grammar constraints red...
Moonseok Choi, Jongwon Jeong, Minki Kang et al.· 0 citations
Sampling multiple chain-of-thought rationales from a language model can uncover correct solutions missed by a single attempt. However, these rationales are typically lengthy, making repeated autoregressive generation costly. Continuous latent reasoning offers a compact alternative, but point-valued methods condition re...
Mingyeong Kim, Gyu-Hwung Cho, Juho Lee et al.· 0 citations
This work forms a KL-regularized objective whose optimum induces a Gibbs policy over final actions under a Gaussian-smoothed behavior prior, and introduces Proposal-Conditioned Refinement Flows (PReFlow), a policy extraction method combining critic-based proposal selection with a conditional refinement flow.
Junhyun Ha, Juho Lee, Byoungwoo Park· arXiv.org· 0 citations
Multi-teacher on-policy distillation (MOPD) combines independently developed domain teachers into a single student by distilling their predictions on student-generated samples. We study a setting where teachers share a reference model but undergo different post-training procedures, and find that MOPD can struggle to re...
Seong-Jang Kim, Chaeyun Jang, Noah Lee et al.· arXiv.org· 2 citations· ⚡1
ChronoFlow is proposed, a unified hierarchical flow matching framework organized by statistical granularity that turns a complex joint generation problem into structurally aligned subproblems while preserving their dependencies.
Changhun Kim, S. Jang, Jeongjun Lee et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.