{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T14:47:03Z","timestamp":1730213223290,"version":"3.28.0"},"reference-count":62,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,16]],"date-time":"2024-06-16T00:00:00Z","timestamp":1718496000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,16]],"date-time":"2024-06-16T00:00:00Z","timestamp":1718496000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,16]]},"DOI":"10.1109\/cvpr52733.2024.02554","type":"proceedings-article","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T17:34:53Z","timestamp":1726508093000},"page":"27037-27047","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Text: Frozen Large Language Models in Visual Signal Comprehension"],"prefix":"10.1109","author":[{"given":"Lei","family":"Zhu","sequence":"first","affiliation":[{"name":"Pnking University"}]},{"given":"Fangyun","family":"Wei","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}]},{"given":"Yanye","family":"Lu","sequence":"additional","affiliation":[{"name":"Pnking University"}]}],"member":"263","reference":[{"key":"ref1","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","article-title":"Palm 2 technical report","author":"Anil","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","first-page":"1877","article-title":"Lan-guage models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv preprint"},{"volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90% chatgpt quality.","author":"Chiang","key":"ref5"},{"key":"ref6","article-title":"Palm: Scaling language modeling with pathways","author":"Chowdhery","year":"2022","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Paul","year":"2017","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref9","article-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Raft: Reward ranked finetuning for generative foundation model alignment","author":"Dong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Glm: General language model pretraining with autoregressive blank infilling","author":"Du","year":"2021","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref13","article-title":"Llama-adapter v2: Parameter-efficient visual instruction model","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Im-proving alignment of dialogue agents via targeted human judgements","author":"Glaese","year":"2022","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2022","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Lora: Low-rank adaptation of large language models","author":"Edward","year":"2021","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/CVPR52729.2023.02164"},{"key":"ref18","article-title":"Panda llm: Training data and evaluation for open-sourced chinese instruction-following large language models","author":"Jiao","year":"2023","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.18653\/v1\/D18-2012"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref21","article-title":"Otter: A multimodal model with in-context instruction tuning","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Blip-2: Bootstrapping language-image pretraining with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Language quan-tized autoencoders: Towards unsupervised text-image alignment","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Cheap and quick: Efficient vision-language instruction tuning for large language models","author":"Luo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Metaicl: Learning to learn in context","author":"Min","year":"2021","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Re-thinking the role of demonstrations: What makes in-context learning work?","author":"Min","year":"2022","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Webgpt: Browser-assisted question-answering with human feedback","author":"Nakano","year":"2021","journal-title":"arXiv preprint"},{"year":"2023","journal-title":"OpenAI","article-title":"Gpt-4 technical report","key":"ref30"},{"key":"ref31","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems, 35"},{"key":"ref32","first-page":"10775","article-title":"Gen-erating diverse structure for image inpainting with hierarchi-cal vq-vae","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Peng"},{"key":"ref33","article-title":"Beit v2: Masked image modeling with vector-quantized visual tokenizers","author":"Peng","year":"2022","journal-title":"arXiv preprint"},{"year":"2018","author":"Radford","journal-title":"Improving language understanding by generative pretraining","key":"ref34"},{"issue":"8","key":"ref35","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref37","article-title":"Direct preference optimization: Your language model is secretly a reward model","author":"Rafailov","year":"2023","journal-title":"arXiv preprint"},{"issue":"1","key":"ref38","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref39","article-title":"Gener-ating diverse high-fidelity images with vq-vae-2","volume":"32","author":"Razavi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref40","article-title":"Exploring models and data for image question answering","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref41","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.18653\/v1\/p16-1162"},{"key":"ref43","article-title":"Alexatm 20b: Few-shot learning using a large-scale multi-lingual seq2seq model","author":"Soltan","year":"2022","journal-title":"arXiv preprint"},{"issue":"2","key":"ref44","volume-title":"Stanford alpaca: an instruction-following llama model","volume":"1","author":"Taori","year":"2023"},{"key":"ref45","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume":"34","author":"Tsimpoukelli","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref48","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref49","article-title":"Visionllm: Large language model is also an open-ended decoder for vision-centric tasks","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Visual chatgpt: Talking, drawing and editing with visual foundation models","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Doctorglm: Fine-tuning your chinese doctor is not a herculean task","author":"Xiong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Vector-quantized image modeling with improved vqgan","author":"Yu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Spae: Semantic pyramid autoencoder for multimodal generation with frozen llms","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Language model beats diffusion-tokenizer is key to visual generation","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref56","DOI":"10.1109\/CVPR52729.2023.01771"},{"key":"ref57","article-title":"Llama-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Opt: Open pretrained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Controllable text-to-image generation with gpt-4","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Pmc-vqa: Vi-sual instruction tuning for medical visual question answering","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref61","DOI":"10.1145\/3581783.3611863"},{"key":"ref62","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","start":{"date-parts":[[2024,6,16]]},"location":"Seattle, WA, USA","end":{"date-parts":[[2024,6,22]]}},"container-title":["2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10654794\/10654797\/10657022.pdf?arnumber=10657022","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,21]],"date-time":"2024-09-21T05:14:30Z","timestamp":1726895670000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10657022\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,16]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/cvpr52733.2024.02554","relation":{},"subject":[],"published":{"date-parts":[[2024,6,16]]}}}