{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/visionllm-large-language-model-is-also-an","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","arxiv_id":"2305.11175","date":"2023-05-18","proceeding":"NeurIPS 2023 11","authors":["Wenhai Wang","Zhe Chen","Xiaokang Chen","Jiannan Wu","Xizhou Zhu","Gang Zeng","Ping Luo","Tong Lu","Jie zhou","Yu Qiao","Jifeng Dai"],"abstract":"Large language models (LLMs) have notably accelerated progress towards artificial general intelligence (AGI), with their impressive zero-shot capacity for user-tailored tasks, endowing them with immense potential across a range of applications. However, in the field of computer vision, despite the availability of numerous powerful vision foundation models (VFMs), they are still restricted to tasks in a pre-defined form, struggling to match the open-ended task capabilities of LLMs. In this work, we present an LLM-based framework for vision-centric tasks, termed VisionLLM. This framework provides a unified perspective for vision and language tasks by treating images as a foreign language and aligning vision-centric tasks with language tasks that can be flexibly defined and managed using language instructions. An LLM-based decoder can then make appropriate predictions based on these instructions for open-ended tasks. Extensive experiments show that the proposed VisionLLM can achieve different levels of task customization through language instructions, from fine-grained object-level to coarse-grained task-level customization, all with good results. It's noteworthy that, with a generalist LLM-based framework, our model can achieve over 60\\% mAP on COCO, on par with detection-specific models. We hope this model can set a new baseline for generalist vision and language models. The demo shall be released based on https://github.com/OpenGVLab/InternGPT. The code shall be released at https://github.com/OpenGVLab/VisionLLM.","url_abs":"https://arxiv.org/abs/2305.11175v2","url_pdf":"https://arxiv.org/pdf/2305.11175v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"visionllm-large-language-model-is-also-an","repo_url":"https://github.com/opengvlab/visionllm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"visionllm-large-language-model-is-also-an","repo_url":"https://github.com/opengvlab/interngpt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.11175","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11175"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opengvlab/interngpt","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opengvlab/visionllm","reach":null}],"summary":{"ran_honours":1,"ran_violates":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"ec3ec9bdfb6d1a6d","entry":"flatten_list","repo":"opengvlab/visionllm","repo_kind":"official","path":"VisionLLMv2/apex/apex/RNN/RNNBackend.py","file_url":"https://github.com/opengvlab/visionllm/blob/HEAD/VisionLLMv2/apex/apex/RNN/RNNBackend.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ec3ec9bdfb6d1a6d"}},{"code_sha256_prefix":"c3c4be397437fd8e","entry":"is_iterable","repo":"opengvlab/visionllm","repo_kind":"official","path":"VisionLLMv2/apex/apex/RNN/RNNBackend.py","file_url":"https://github.com/opengvlab/visionllm/blob/HEAD/VisionLLMv2/apex/apex/RNN/RNNBackend.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c3c4be397437fd8e"}},{"code_sha256_prefix":"c37951874246965f","entry":"jit_dropout_add","repo":"opengvlab/visionllm","repo_kind":"official","path":"VisionLLMv2/apex/apex/contrib/multihead_attn/encdec_multihead_attn.py","file_url":"https://github.com/opengvlab/visionllm/blob/HEAD/VisionLLMv2/apex/apex/contrib/multihead_attn/encdec_multihead_attn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c37951874246965f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}