Watch-Think-Interact (WTI), a closed-loop framework for multi-question streaming video reasoning that maintains compact natural-language memory entries tagged with source-video time ranges, achieves state-of-the-art aggregate performance among the compared open-source streaming baselines.
Zi-Heng Huang, Yi-Cheng Bao, Xue-Heng Li et al.· 0 citations
Historical photographs and other canonical images can now be edited seamlessly with a single instruction, often leaving no reliable pixel-level trace. In such cases, the only evidence of manipulation may be a fact about what the image depicts. Existing benchmarks instead rely on generator artefacts, image-caption incon...
Yi-Cheng Bao, Zhen-Kun Gao, Xia-Hui Guo et al.· 0 citations
This paper presents IterCAD, a unified multimodal agent framework for closed-loop, interactive CAD generation and editing, and introduces the IterCAD-Bench evaluation suite, establishing a survivor-bias-free standard that unifies code validity and geometric precision.
Tao Hu, Jiaxin Ai, Licheng Wen et al.· arXiv.org· 8 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.