Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Does Semantic Noise Initialization Transfer from Images to Videos? A Paired Diagnostic Study
Yixiao Jing, Chaoyu Zhang, Zixuan Zhong +1
Semantic noise initialization has been reported to improve robustness and controllability in image diffusion models. Whether these gains transfer to text-to-video (T2V) generation…
cs.CV2026
MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents
Peizhou Huang, Zixuan Zhong, Zhongwei Wan +12
Deep Research Agents (DRAs) generate citation-rich reports via multi-step search and synthesis, yet existing benchmarks mainly target text-only settings or short-form multimodal QA…