https://openreview.net/forum?id=F1ff8zcjPp&referrer=%5Bthe%20profile%20of%20Yue%20Dong%5D(%2Fprofile%3Fid%3D~Yue_Dong2)
Vision-language models (VLMs) have improved significantly in their capabilities, but their complex architecture makes their safety alignment challenging. In...
layerwisealignmentexaminingsafety
https://openreview.net/forum?id=IQTGyOh8f9&referrer=%5Bthe%20profile%20of%20Seung%20Hyun%20Lee%5D(%2Fprofile%3Fid%3D~Seung_Hyun_Lee2)
The goal of image cropping is to identify visually appealing crops in an image. Conventional methods are trained on specific datasets and fail to adapt to new...
vision language modelimage croppingcroppercontext
https://openreview.net/forum?id=ELd5Kn0StP&referrer=%5Bthe%20profile%20of%20Xiaohong%20Liu%5D(%2Fprofile%3Fid%3D~Xiaohong_Liu2)
The development of multimodal large language models (MLLMs) enables the evaluation of image quality through natural language descriptions. This advancement...
image quality assessmentmultimodal languagegroundingiqamodel
https://openreview.net/forum?id=KCZU12jzfC&referrer=%5Bthe%20profile%20of%20Harold%20Haodong%20Chen%5D(%2Fprofile%3Fid%3D~Harold_Haodong_Chen1)
Accurately profiling urban regions in terms of social, economic and environmental indicators is crucial for urban planning and sustainable development. The...
urban regionlearningtextenhancedprofiling
https://scirp.org/journal/papercitationdetails?paperid=124836&JournalID=2431
Research on specific domain question-answering technology has become important with the increasing demand for intelligent question-answering systems. This...
question answeringdomainalgorithmbasedcontrastive
https://j-min.io/publication/sevila_neurips2023/
Sep 22, 2023 - To handle video QA, we self-chain BLIP-2 for 2-stage inference (localize+QA) & refining localization via QA feedback - *[NeurIPS...
image languagevideo localizationselfchainedmodel
https://www.hindustantimes.com/videos/news/china-rocket-image-row-bjps-mandarin-language-birthday-wish-for-mk-stalin-isro-tamil-nadu-101709316328813-amp.html
BJP took a fresh jibe at Tamil Nadu CM MK Stalin while extending birthday wishes. The BJP, in a post on 'X' platform, wished CM Stalin in Mandarin - a form of...
mandarin languagebirthday wishchinarocketimage
https://imgur.com/a/0G8MCHJ
Discover the magic of the internet at Imgur, a community powered entertainment destination. Lift your spirits with funny jokes, trending memes, entertaining...
english languageimagepostoriginalfacebook
https://www.nature.com/articles/s41550-025-02670-z?error=cookies_not_supported&code=b1e206de-5480-4e3f-9d79-85ce84503c14
Oct 8, 2025 - Large language models can describe and classify changing objects in astronomical images with high accuracy. This enables searches for visual features using...
large language modelstextualinterpretationtransientimage