{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/kosmos-2-grounding-multimodal-large-language","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","arxiv_id":"2306.14824","date":"2023-06-26","proceeding":null,"authors":["Zhiliang Peng","Wenhui Wang","Li Dong","Yaru Hao","Shaohan Huang","Shuming Ma","Furu Wei"],"abstract":"We introduce Kosmos-2, a Multimodal Large Language Model (MLLM), enabling new capabilities of perceiving object descriptions (e.g., bounding boxes) and grounding text to the visual world. Specifically, we represent refer expressions as links in Markdown, i.e., ``[text span](bounding boxes)'', where object descriptions are sequences of location tokens. Together with multimodal corpora, we construct large-scale data of grounded image-text pairs (called GrIT) to train the model. In addition to the existing capabilities of MLLMs (e.g., perceiving general modalities, following instructions, and performing in-context learning), Kosmos-2 integrates the grounding capability into downstream applications. We evaluate Kosmos-2 on a wide range of tasks, including (i) multimodal grounding, such as referring expression comprehension, and phrase grounding, (ii) multimodal referring, such as referring expression generation, (iii) perception-language tasks, and (iv) language understanding and generation. This work lays out the foundation for the development of Embodiment AI and sheds light on the big convergence of language, multimodal perception, action, and world modeling, which is a key step toward artificial general intelligence. Code and pretrained models are available at https://aka.ms/kosmos-2.","url_abs":"https://arxiv.org/abs/2306.14824v3","url_pdf":"https://arxiv.org/pdf/2306.14824v3.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":"kosmos-2-grounding-multimodal-large-language","repo_url":"https://github.com/microsoft/unilm/tree/master/kosmos-2","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"kosmos-2-grounding-multimodal-large-language","repo_url":"https://github.com/rabiulcste/vqazero","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"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"},{"task_slug":"multimodal-large-language-model","task_name":"Multimodal Large Language Model"},{"task_slug":"phrase-grounding","task_name":"Phrase Grounding"},{"task_slug":"referring-expression","task_name":"Referring Expression"},{"task_slug":"referring-expression-comprehension","task_name":"Referring Expression Comprehension"},{"task_slug":"referring-expression-generation","task_name":"Referring expression generation"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-vip-bench","task":"Visual Question Answering","dataset":"ViP-Bench","model":"Kosmos-2 (Discrete Token)","rank_in_archive_order":13,"of":13,"metrics":{"GPT-4 score (bbox)":"26.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2306.14824","atlas_url":"https://app.syntology.ai/?focus=2306.14824","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2306.14824"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2306.14824\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2306.14824"},"call":"get_concepts_for_paper(arxiv_id=\"2306.14824\")"}],"by_repo":[{"repo":"microsoft/unilm","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["2002.12804","2106.08254","2203.00555","2601.23174"],"harvested_for_calls":[{"arxiv_id":"2002.12804","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2002.12804"},"call":"get_harvested_code_for_paper(arxiv_id=\"2002.12804\")"},{"arxiv_id":"2106.08254","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.08254"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.08254\")"},{"arxiv_id":"2203.00555","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2203.00555"},"call":"get_harvested_code_for_paper(arxiv_id=\"2203.00555\")"},{"arxiv_id":"2601.23174","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2601.23174"},"call":"get_harvested_code_for_paper(arxiv_id=\"2601.23174\")"}]},{"repo":"rabiulcste/vqazero","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2306.09996"],"harvested_for_calls":[{"arxiv_id":"2306.09996","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2306.09996"},"call":"get_harvested_code_for_paper(arxiv_id=\"2306.09996\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"2aa30b060a855739ab342d4b4db0aaf3f6d0e1d647feadd3270975beda47bafa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}