VAR has gained widespread popularity due to its next-scale prediction paradigm. However, it faces substantial performance bottlenecks when handling complex scenes with multiple objects and attributes. Existing diffusion-based enhancement methods fail to adequately address the unique challenge of cross-scale error propa...
Zhen-Nan Chen, Tianxing Shi, Pengcheng Xu et al.· 0 citations
This paper investigates an increasingly important topic in generative modeling: pixel-space diffusion models. Although numerous studies have explored this topic, most focus on small-scale or class-conditional settings. Consequently, a practical recipe for training pixel-space models that rival or exceed well-establishe...
Deng-Yang Jiang, Ruoyi Du, Zhen-Nan Chen et al.· 3 citations
Learning-based memory systems for self-evolving LLM agents face two tightly coupled challenges. First, trajectory-indexed utilities grow with the interaction history, thereby dispersing limited feedback over an ever-expanding state space. Second, because trajectory-level rewards are jointly assigned to co-retrieved mem...
Yi Yang, Zhen-Nan Chen, Yihong Zhuang et al.· 0 citations
This work proposes Convex Hull Neighborhood Smooth Dual Generalization (CSDG), which expresses the Bellman backup as an in-sample value target plus a CHN-local correction, and characterize the implicit policies induced by the idealized operators and give a conditional non-degradation criterion.
Yi Yang, Zhen-Nan Chen, Mingfeng Lv et al.· 0 citations
Paint-Anything is presented, which learns a shared hex-prompt interface for generation and editing through object-level color supervision, and introduces Any Color Benchmark (ACBench), comprising ACBench-T2I and ACBench-Edit, to measure object-level hex color fidelity across both tasks.
Ji Xie, Dewei Zhou, Xin-Yu Huang 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.