{"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/longllava-scaling-multi-modal-llms-to-1000","title":"LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture","arxiv_id":"2409.02889","date":"2024-09-04","proceeding":null,"authors":["Xidong Wang","Dingjie Song","Shunian Chen","Chen Zhang","Benyou Wang"],"abstract":"Expanding the long-context capabilities of Multi-modal Large Language Models~(MLLMs) is crucial for video understanding, high-resolution image understanding, and multi-modal agents. This involves a series of systematic optimizations, including model architecture, data construction and training strategy, particularly addressing challenges such as \\textit{degraded performance with more images} and \\textit{high computational costs}. In this paper, we adapt the model architecture to a hybrid of Mamba and Transformer blocks, approach data construction with both temporal and spatial dependencies among multiple images and employ a progressive training strategy. The released model \\textbf{LongLLaVA}~(\\textbf{Long}-Context \\textbf{L}arge \\textbf{L}anguage \\textbf{a}nd \\textbf{V}ision \\textbf{A}ssistant) is the first hybrid MLLM, which achieved a better balance between efficiency and effectiveness. LongLLaVA not only achieves competitive results across various benchmarks, but also maintains high throughput and low memory consumption. Especially, it could process nearly a thousand images on a single A100 80GB GPU, showing promising application prospects for a wide range of tasks.","url_abs":"https://arxiv.org/abs/2409.02889v2","url_pdf":"https://arxiv.org/pdf/2409.02889v2.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":"longllava-scaling-multi-modal-llms-to-1000","repo_url":"https://github.com/freedomintelligence/longllava","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"mamba","task_name":"Mamba"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"mamba","method_name":"Mamba"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2409.02889","atlas_url":"https://app.syntology.ai/?focus=2409.02889","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02889"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2409.02889"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2409.02889"},"call":"get_harvested_code_for_paper(arxiv_id=\"2409.02889\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2409.02889"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2409.02889\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2409.02889"},"call":"get_concepts_for_paper(arxiv_id=\"2409.02889\")"}],"by_repo":[{"repo":"freedomintelligence/longllava","kind":"official","samples":7,"ran":7,"instrument":5,"unverified":0}],"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","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2409.02889.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2409.02889.svg"},"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/freedomintelligence/longllava","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":4,"ran":1,"ran_honours":1,"ran_fixture":1},"n_samples":7,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":0,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":7,"ran":7,"n_ran_checked":2,"n_instrument":5,"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":7,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":5,"n_ran_without_level_date":2,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"8e7a1ecf0e0160a0","code_sha256_prefix":"8e7a1ecf0e0160a0","entry":"extract_and_choose_answer","repo":"freedomintelligence/longllava","repo_kind":"official","path":"benchmarks/MVBench/generate_score.py","file_url":"https://github.com/freedomintelligence/longllava/blob/HEAD/benchmarks/MVBench/generate_score.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"pattern:str/0/str, model_answer:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"8e7a1ecf0e0160a0"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, freedomintelligence/longllava when it was checked","mcp_get_code":{"code_sha256":"8e7a1ecf0e0160a0"}},{"code_sha256":"36c5e1ece4a3bca1","code_sha256_prefix":"36c5e1ece4a3bca1","entry":"extract_and_choose_answer","repo":"freedomintelligence/longllava","repo_kind":"official","path":"benchmarks/VIAH/generate_score.py","file_url":"https://github.com/freedomintelligence/longllava/blob/HEAD/benchmarks/VIAH/generate_score.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"pattern:str/0/str, model_answer:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"36c5e1ece4a3bca1"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, freedomintelligence/longllava when it was checked","mcp_get_code":{"code_sha256":"36c5e1ece4a3bca1"}},{"code_sha256":"42a46570620cd9fa","code_sha256_prefix":"42a46570620cd9fa","entry":"get_chunk","repo":"freedomintelligence/longllava","repo_kind":"official","path":"benchmarks/MVBench/model_mvbench_qa.py","file_url":"https://github.com/freedomintelligence/longllava/blob/HEAD/benchmarks/MVBench/model_mvbench_qa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"signature":"lst:list/1/int, n:int/0/int, k:int/0/int","fixture_out_type":"list","retrieve_with":{"tool":"get_code","code_sha256":"42a46570620cd9fa"},"code_page":"/code/get-chunk","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, freedomintelligence/longllava when it was checked","mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"code_sha256":"d51fcf23e1e8c26f","code_sha256_prefix":"d51fcf23e1e8c26f","entry":"load_image","repo":"freedomintelligence/longllava","repo_kind":"official","path":"llava/mm_utils.py","file_url":"https://github.com/freedomintelligence/longllava/blob/HEAD/llava/mm_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"image:BytesIO/0/?","fixture_out_type":"Image","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/load-image","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, freedomintelligence/longllava when it was checked","mcp_get_code":{"code_sha256":"d51fcf23e1e8c26f"}},{"code_sha256":"468eedeba67f1b00","code_sha256_prefix":"468eedeba67f1b00","entry":"resize_and_pad_image","repo":"freedomintelligence/longllava","repo_kind":"official","path":"llava/mm_utils.py","file_url":"https://github.com/freedomintelligence/longllava/blob/HEAD/llava/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"image:Image/0/?, target_resolution:tuple/1/int","fixture_out_type":"Image","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/resize-and-pad-image","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, freedomintelligence/longllava when it was checked","mcp_get_code":{"code_sha256":"468eedeba67f1b00"}},{"code_sha256":"3999ff487573f32c","code_sha256_prefix":"3999ff487573f32c","entry":"select_best_resolution","repo":"freedomintelligence/longllava","repo_kind":"official","path":"llava/mm_utils.py","file_url":"https://github.com/freedomintelligence/longllava/blob/HEAD/llava/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"signature":"original_size:tuple/1/int, possible_resolutions:list/1/tuple","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/select-best-resolution","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, freedomintelligence/longllava when it was checked","mcp_get_code":{"code_sha256":"3999ff487573f32c"}},{"code_sha256":"076c252c52cbb161","code_sha256_prefix":"076c252c52cbb161","entry":"split_list","repo":"freedomintelligence/longllava","repo_kind":"official","path":"benchmarks/MVBench/model_mvbench_qa.py","file_url":"https://github.com/freedomintelligence/longllava/blob/HEAD/benchmarks/MVBench/model_mvbench_qa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"lst:list/1/int, n:int/0/int","fixture_out_type":"list","retrieve_with":{"tool":"get_code","code_sha256":"076c252c52cbb161"},"code_page":"/code/split-list","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, freedomintelligence/longllava when it was checked","mcp_get_code":{"code_sha256":"076c252c52cbb161"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b5966570e417737f73e71ce2b32bbda35e64ff921f40aefc442c94d6f24266c2","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}