{"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/prismatic-vlms-investigating-the-design-space","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","arxiv_id":"2402.07865","date":"2024-02-12","proceeding":null,"authors":["Siddharth Karamcheti","Suraj Nair","Ashwin Balakrishna","Percy Liang","Thomas Kollar","Dorsa Sadigh"],"abstract":"Visually-conditioned language models (VLMs) have seen growing adoption in applications such as visual dialogue, scene understanding, and robotic task planning; adoption that has fueled a wealth of new models such as LLaVa, InstructBLIP, and PaLI-3. Despite the volume of new releases, key design decisions around image preprocessing, architecture, and optimization are under-explored, making it challenging to understand what factors account for model performance $-$ a challenge further complicated by the lack of objective, consistent evaluations. To address these gaps, we first compile a suite of standardized evaluations spanning visual question answering, object localization, and challenge sets that probe properties such as hallucination; evaluations that provide fine-grained insight VLM capabilities. Second, we rigorously investigate VLMs along key design axes, including pretrained visual representations and training from base vs. instruct-tuned language models, amongst others. We couple our analysis with three resource contributions: (1) a unified framework for evaluating VLMs, (2) optimized, flexible training code, and (3) checkpoints for all models, including a family of VLMs at the 7-13B scale that strictly outperform InstructBLIP and LLaVa v1.5, the state-of-the-art in open VLMs.","url_abs":"https://arxiv.org/abs/2402.07865v2","url_pdf":"https://arxiv.org/pdf/2402.07865v2.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":"prismatic-vlms-investigating-the-design-space","repo_url":"https://github.com/tri-ml/prismatic-vlms","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"prismatic-vlms-investigating-the-design-space","repo_url":"https://github.com/tri-ml/vlm-evaluation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"prismatic-vlms-investigating-the-design-space","repo_url":"https://github.com/RylanSchaeffer/prismatic-vlms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"task-planning","task_name":"Task Planning"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.07865","atlas_url":"https://app.syntology.ai/?focus=2402.07865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07865"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/tri-ml/vlm-evaluation","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/RylanSchaeffer/prismatic-vlms","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tri-ml/prismatic-vlms","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"ran":1,"repositories":2}},"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":4,"samples":[{"code_sha256_prefix":"6e9a835262e7ec57","entry":"initialize_overwatch","repo":"tri-ml/prismatic-vlms","repo_kind":"official","path":"prismatic/overwatch/overwatch.py","file_url":"https://github.com/tri-ml/prismatic-vlms/blob/HEAD/prismatic/overwatch/overwatch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6e9a835262e7ec57"}},{"code_sha256_prefix":"08e6aeaa327cb1f2","entry":"ImageProcessor","repo":"tri-ml/vlm-evaluation","repo_kind":"official","path":"vlm_eval/models/prismatic.py","file_url":"https://github.com/tri-ml/vlm-evaluation/blob/HEAD/vlm_eval/models/prismatic.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"08e6aeaa327cb1f2"}},{"code_sha256_prefix":"1c76ba920eb87f9b","entry":"PrismaticVLM","repo":"tri-ml/vlm-evaluation","repo_kind":"official","path":"vlm_eval/models/prismatic.py","file_url":"https://github.com/tri-ml/vlm-evaluation/blob/HEAD/vlm_eval/models/prismatic.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1c76ba920eb87f9b"}},{"code_sha256_prefix":"e0633b98873dbfc7","entry":"Tokenizer","repo":"tri-ml/vlm-evaluation","repo_kind":"official","path":"vlm_eval/models/prismatic.py","file_url":"https://github.com/tri-ml/vlm-evaluation/blob/HEAD/vlm_eval/models/prismatic.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e0633b98873dbfc7"}},{"code_sha256_prefix":"a2488e8a8252030f","entry":"VLM","repo":"tri-ml/vlm-evaluation","repo_kind":"official","path":"vlm_eval/models/prismatic.py","file_url":"https://github.com/tri-ml/vlm-evaluation/blob/HEAD/vlm_eval/models/prismatic.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a2488e8a8252030f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}