{"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/vila-on-pre-training-for-visual-language","title":"VILA: On Pre-training for Visual Language Models","arxiv_id":"2312.07533","date":"2023-12-12","proceeding":"CVPR 2024 1","authors":["Ji Lin","Hongxu Yin","Wei Ping","Yao Lu","Pavlo Molchanov","Andrew Tao","Huizi Mao","Jan Kautz","Mohammad Shoeybi","Song Han"],"abstract":"Visual language models (VLMs) rapidly progressed with the recent success of large language models. There have been growing efforts on visual instruction tuning to extend the LLM with visual inputs, but lacks an in-depth study of the visual language pre-training process, where the model learns to perform joint modeling on both modalities. In this work, we examine the design options for VLM pre-training by augmenting LLM towards VLM through step-by-step controllable comparisons. We introduce three main findings: (1) freezing LLMs during pre-training can achieve decent zero-shot performance, but lack in-context learning capability, which requires unfreezing the LLM; (2) interleaved pre-training data is beneficial whereas image-text pairs alone are not optimal; (3) re-blending text-only instruction data to image-text data during instruction fine-tuning not only remedies the degradation of text-only tasks, but also boosts VLM task accuracy. With an enhanced pre-training recipe we build VILA, a Visual Language model family that consistently outperforms the state-of-the-art models, e.g., LLaVA-1.5, across main benchmarks without bells and whistles. Multi-modal pre-training also helps unveil appealing properties of VILA, including multi-image reasoning, enhanced in-context learning, and better world knowledge.","url_abs":"https://arxiv.org/abs/2312.07533v4","url_pdf":"https://arxiv.org/pdf/2312.07533v4.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":"vila-on-pre-training-for-visual-language","repo_url":"https://github.com/efficient-large-model/vila","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"vila-on-pre-training-for-visual-language","repo_url":"https://github.com/mit-han-lab/llm-awq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"vila-on-pre-training-for-visual-language","repo_url":"https://github.com/nvlabs/vila","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"world-knowledge","task_name":"World Knowledge"},{"task_slug":"zeroshot-video-question-answer","task_name":"Zero-Shot Video Question Answer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"VILA-13B","rank_in_archive_order":79,"of":231,"metrics":{"GPT-4 score":"45.7"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-msvd-qa","task":"Zero-Shot Video Question Answer","dataset":"MSVD-QA","model":"VILA1.5-40B","rank_in_archive_order":4,"of":28,"metrics":{"Accuracy":"80.1"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-video-mme-1","task":"Zero-Shot Video Question Answer","dataset":"Video-MME","model":"VILA-1.5 (34B)","rank_in_archive_order":7,"of":11,"metrics":{"Accuracy (%)":"64.1"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-video-mme","task":"Zero-Shot Video Question Answer","dataset":"Video-MME (w/o subs)","model":"VILA-1.5 (34B)","rank_in_archive_order":7,"of":9,"metrics":{"Accuracy (%)":"61.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.07533","atlas_url":"https://app.syntology.ai/?focus=2312.07533","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":"2312.07533"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2312.07533\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2312.07533"},"call":"get_concepts_for_paper(arxiv_id=\"2312.07533\")"}],"by_repo":[{"repo":"efficient-large-model/vila","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2503.19903"],"harvested_for_calls":[{"arxiv_id":"2503.19903","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2503.19903"},"call":"get_harvested_code_for_paper(arxiv_id=\"2503.19903\")"}]},{"repo":"mit-han-lab/llm-awq","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2505.03031"],"harvested_for_calls":[{"arxiv_id":"2505.03031","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2505.03031"},"call":"get_harvested_code_for_paper(arxiv_id=\"2505.03031\")"}]},{"repo":"nvlabs/vila","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2503.19903"],"harvested_for_calls":[{"arxiv_id":"2503.19903","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2503.19903"},"call":"get_harvested_code_for_paper(arxiv_id=\"2503.19903\")"}]}],"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":"5c97171517a87919aceb4d1a5d4ca885e836870c019af64b210ce2d61728264c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}