Regression-based RL for flow models mandates sampling \emph{without} classifier-free guidance (CFG) to align the rectification target with the reference marginal velocity. Extending Advantage-Weighted Rectification (AWR), which dynamically scales this regression target based on reward, to video generation encounters a...
Zhe-Ming Fu, Wen-Bin Ning, R.-Z. He et al.· 0 citations
This work presents MedUP, a Med-VLM that natively unifies perception and understanding within a shared token space, and curates UniMed-Train, a 1.84M-instance corpus spanning text-guided segmentation, region-grounded understanding, medical VQA and CoT-based segmentation, and introduces UniMed-Bench for unified evaluati...
Yuan Wang, Hualiang Wang, Yixin Chen et al.· 0 citations
On-policy distillation, in which a teacher corrects samples that the student itself generates, presupposes that the two models speak the same language: identical VAE latents, matching architectures, and a common timestep grid. We ask what happens when none of this holds, as when the strongest teacher available and the...
The method combines chunk-wise autoregressive adaptation, Source-Anchored Distribution Matching Distillation, and Long-Horizon Autoregressive Distillation to reduce train--inference mismatch, preserve source fidelity during two-step generation, and mitigate accumulated temporal drift.
Yi-Cheng Xiao, Wenxun Dai, Xinran Qin et al.· 5 citations
This paper presents Poly-OPD, a framework that can consolidate complementary strengths of heterogeneous teachers into a single compact flow-matching student, and uses a gradient compatibility diagnostic to organize its adapters.
Perceptual Flow Matching supervises flow matching in a perceptual feature space using pretrained perceptual models, which substantially improves the few-step generation capability of flow-matching models, reducing the number of sampling steps from 35-50 to 4-8 while preserving generation quality.
Chuyang Zhao, Yifei Song, Hongfa Wang et al.· arXiv.org· 2 citations
VLTok is a novel 1D hybrid tokenizer that unifies V isual and L anguage representations in a shared Tok en space through a self-prompted training paradigm, and achieves state-of-the-art performance in both image reconstruction and image generation.
Hualiang Wang, Siming Fu, Wei-Nan Jia et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
