{"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/perceptionlm-open-access-data-and-models-for","title":"PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding","arxiv_id":"2504.13180","date":"2025-04-17","proceeding":null,"authors":["Jang Hyun Cho","Andrea Madotto","Effrosyni Mavroudi","Triantafyllos Afouras","Tushar Nagarajan","Muhammad Maaz","Yale Song","Tengyu Ma","Shuming Hu","Suyog Jain","Miguel Martin","Huiyu Wang","Hanoona Rasheed","Peize Sun","Po-Yao Huang","Daniel Bolya","Nikhila Ravi","Shashank Jain","Tammy Stark","Shane Moon","Babak Damavandi","Vivian Lee","Andrew Westbury","Salman Khan","Philipp Krähenbühl","Piotr Dollár","Lorenzo Torresani","Kristen Grauman","Christoph Feichtenhofer"],"abstract":"Vision-language models are integral to computer vision research, yet many high-performing models remain closed-source, obscuring their data, design and training recipe. The research community has responded by using distillation from black-box models to label training data, achieving strong benchmark results, at the cost of measurable scientific progress. However, without knowing the details of the teacher model and its data sources, scientific progress remains difficult to measure. In this paper, we study building a Perception Language Model (PLM) in a fully open and reproducible framework for transparent research in image and video understanding. We analyze standard training pipelines without distillation from proprietary models and explore large-scale synthetic data to identify critical data gaps, particularly in detailed video understanding. To bridge these gaps, we release 2.8M human-labeled instances of fine-grained video question-answer pairs and spatio-temporally grounded video captions. Additionally, we introduce PLM-VideoBench, a suite for evaluating challenging video understanding tasks focusing on the ability to reason about \"what\", \"where\", \"when\", and \"how\" of a video. We make our work fully reproducible by providing data, training recipes, code & models.","url_abs":"https://arxiv.org/abs/2504.13180v1","url_pdf":"https://arxiv.org/pdf/2504.13180v1.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":"perceptionlm-open-access-data-and-models-for","repo_url":"https://github.com/facebookresearch/perception_models","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-question-answering-on-next-qa","task":"Video Question Answering","dataset":"NExT-QA","model":"PLM-8B","rank_in_archive_order":4,"of":47,"metrics":{"Accuracy":"84.1"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-next-qa","task":"Video Question Answering","dataset":"NExT-QA","model":"PLM-3B","rank_in_archive_order":6,"of":47,"metrics":{"Accuracy":"83.4"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-next-qa","task":"Video Question Answering","dataset":"NExT-QA","model":"PLM-1B","rank_in_archive_order":12,"of":47,"metrics":{"Accuracy":"80.3"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-tvbench","task":"Video Question Answering","dataset":"TVBench","model":"PLM-8B","rank_in_archive_order":2,"of":28,"metrics":{"Average Accuracy":"63.5"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-tvbench","task":"Video Question Answering","dataset":"TVBench","model":"PLM-3B","rank_in_archive_order":5,"of":28,"metrics":{"Average Accuracy":"58.9"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-tvbench","task":"Video Question Answering","dataset":"TVBench","model":"PLM-1B","rank_in_archive_order":12,"of":28,"metrics":{"Average Accuracy":"50.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2504.13180","atlas_url":"https://app.syntology.ai/?focus=2504.13180","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":"2504.13180"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2504.13180\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2504.13180"},"call":"get_concepts_for_paper(arxiv_id=\"2504.13180\")"}],"by_repo":[{"repo":"facebookresearch/perception_models","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2504.13181"],"harvested_for_calls":[{"arxiv_id":"2504.13181","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2504.13181"},"call":"get_harvested_code_for_paper(arxiv_id=\"2504.13181\")"}]}],"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":"d55b7261ed65ab69f531ed637abee622133d2320acfbba12825c1fe74dbc5d48","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}