The optimization objective for e-commerce advertising creatives has shifted from aesthetic quality to online business metrics like click-through rate (CTR). Recent methods generate appealing ad images from product images by constructing CTR-based reward signals and refining prompt generation via Reinforcement Learning....
Xu Zhang, Haohan Wang, Zheng Zhang et al.· 0 citations
Multi-view representations enable pretrained image and video vision-language models to understand 3D scenes, but their long visual token sequences make inference costly. Redundancy arises both from repeated observations of the same scene regions across views and from processing all visual tokens at every LLM layer, reg...
Yong-Xing Zheng, Hao Wu, Fang Li et al.· 0 citations
Visual interventions provide a training-free way to reduce hallucinations in multimodal large language models. However, an intervention may have little leverage at some layers and may damage a correct answer even when it changes the output. We investigate where visual interventions retain leverage and when they improve...
Qi-Ji Zhou, Jun-Yi Hu, Pei-Yu Wang et al.· 0 citations
Video editing models achieve strong performance in modifying appearance, backgrounds, styles, and motions, empowered by large-scale training data. Beyond general scenarios, professional motions are significant in performance, sports, and martial arts. This paper focuses on professional motion editing, which involves fi...
Si-Yi Qian, Han-Qing Yang, Wei-Huang Lin et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Vision-language reward models are trained on annotated preference pairs, which are expensive to collect, can disagree, and are ranked by benchmark accuracy. We build one with no human preference label: a linear head on an intermediate layer of a frozen Qwen3-VL backbone, trained to score a web caption above a perturbed...
Yue-Ying Li, Jing-Xuan Fan, Kianté Brantley et al.· 0 citations
Vision-language-action (VLA) models increasingly incorporate intermediate reasoning to improve robotic manipulation, yet existing approaches primarily reason about observed states without explicitly anticipating future scene evolution. Extending such reasoning to explicit future rollouts at every inference step, howeve...
Shenglan Li, Zhendong Mi, Hengyi Zhu et al.· 0 citations
Memes play a central role in modern online communication, especially in contexts of political conflict where visual and textual cues combine to convey persuasive messages. We study persuasive technique detection in Ukrainian memes using vision-language models (VLMs). We introduce UkrMeme, a dataset of 200 organically p...
Nazar Andrushko, Vera Schmitt, Veronika Solopova· 0 citations
Continual learning requires models to accumulate past experience and transfer it to new tasks. Despite substantial research on continual learning, existing work remains largely confined to non-embodied settings, without extending to embodied environments. To address this gap, we introduce EmbodiedCLBench, the first ben...
Jie Huang, Ya-Nan Chen, Rui-Xun Liu et al.· 0 citations
Text-to-image models appear to reproduce the habits of the photographs they learned from. Analog clocks are an extreme case: in advertising, watches almost always show 10:10, and generated clocks return to 10:10 even when another time is requested. We measure this bias and test three ways of overcoming it on 52 models...
By transforming body heat into point clouds for the first time, TAP3D pioneers a new paradigm for privacy-first, fully passive human sensing for many applications, offering significant advantages in cost, density, human sensitivity, and privacy.
Xie Zhang, Cheng-Xiao Li, Xuan Liu et al.· 0 citations
On a film set, the camera move is committed during a take. Generative video reshooting lets filmmakers change it afterward, but may require hallucinating unrecorded content, a gap sometimes discovered only after leaving the set. We present Hybrid Cinematography, a workflow that bridges physical capture and generative r...
Nhan (Nathan), Tran, Neal Wadhwa et al.· 0 citations
Multimodal Large Language Models (MLLMs) have significantly advanced document understanding, yet current Doc-VQA evaluations score only the final answer and leave the supporting evidence unchecked. This answer-only approach masks a critical failure mode: a model can land on the correct answer while grounding it in the...
Dongsheng Ma, Jiayu Li, Zhengren Wang et al.· 0 citations
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
Computer scientist, entrepreneur, and philanthropist will collaborate with the MIT Schwarzman College of Computing to advance AI and scientific discovery.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
