{"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/avg-llava-a-large-multimodal-model-with","title":"AVG-LLaVA: A Large Multimodal Model with Adaptive Visual Granularity","arxiv_id":"2410.02745","date":"2024-09-20","proceeding":null,"authors":["Zhibin Lan","LiQiang Niu","Fandong Meng","Wenbo Li","Jie zhou","Jinsong Su"],"abstract":"Recently, when dealing with high-resolution images, dominant LMMs usually divide them into multiple local images and one global image, which will lead to a large number of visual tokens. In this work, we introduce AVG-LLaVA, an LMM that can adaptively select the appropriate visual granularity based on the input image and instruction. This approach not only reduces the number of visual tokens and speeds up inference, but also improves the overall model performance. Specifically, we introduce the following modules based on LLaVA-NeXT: (a) a visual granularity scaler that includes multiple pooling layers to obtain visual tokens with different granularities; (b) a visual granularity router, which includes a Transformer layer, an MLP layer, and a voter layer, used to select the appropriate visual granularity based on the image and instruction. Furthermore, we propose RGLF, a novel training paradigm that aims at aligning the granularity predicted by the router with the preferences of the LMM, without the need for additional manually annotated data. Extensive experiments and analysis show that AVG-LLaVA achieves superior performance across 11 benchmarks, as well as significantly reduces the number of visual tokens and speeds up inference (e.g., an 85.3% reduction in visual tokens and a 2.53$\\times$ increase in inference speed on the AI2D benchmark).","url_abs":"https://arxiv.org/abs/2410.02745v2","url_pdf":"https://arxiv.org/pdf/2410.02745v2.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":"avg-llava-a-large-multimodal-model-with","repo_url":"https://github.com/deeplearnxmu/avg-llava","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":null,"task_name":"Avg"}],"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":"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":"speed","method_name":"SPEED"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.02745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02745"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/deeplearnxmu/avg-llava","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":3,"ran":3,"ran_violates":1,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"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":0,"samples":[{"code_sha256_prefix":"20e4f665698a3d18","entry":"collate_fn","repo":"deeplearnxmu/avg-llava","repo_kind":"official","path":"llava/eval/model_vqa_loader.py","file_url":"https://github.com/deeplearnxmu/avg-llava/blob/HEAD/llava/eval/model_vqa_loader.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"20e4f665698a3d18"}},{"code_sha256_prefix":"da4dc49187083d73","entry":"collate_fn","repo":"deeplearnxmu/avg-llava","repo_kind":"official","path":"llava/eval/our_model_vqa_loader.py","file_url":"https://github.com/deeplearnxmu/avg-llava/blob/HEAD/llava/eval/our_model_vqa_loader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"da4dc49187083d73"}},{"code_sha256_prefix":"7e03b180fa317c9a","entry":"divide_to_patches","repo":"deeplearnxmu/avg-llava","repo_kind":"official","path":"llava/mm_utils.py","file_url":"https://github.com/deeplearnxmu/avg-llava/blob/HEAD/llava/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7e03b180fa317c9a"}},{"code_sha256_prefix":"42a46570620cd9fa","entry":"get_chunk","repo":"deeplearnxmu/avg-llava","repo_kind":"official","path":"llava/eval/model_vqa.py","file_url":"https://github.com/deeplearnxmu/avg-llava/blob/HEAD/llava/eval/model_vqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"code_sha256_prefix":"bae18947b56f2be1","entry":"is_none","repo":"deeplearnxmu/avg-llava","repo_kind":"official","path":"llava/eval/model_vqa_mmbench.py","file_url":"https://github.com/deeplearnxmu/avg-llava/blob/HEAD/llava/eval/model_vqa_mmbench.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bae18947b56f2be1"}},{"code_sha256_prefix":"468eedeba67f1b00","entry":"resize_and_pad_image","repo":"deeplearnxmu/avg-llava","repo_kind":"official","path":"llava/mm_utils.py","file_url":"https://github.com/deeplearnxmu/avg-llava/blob/HEAD/llava/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"468eedeba67f1b00"}},{"code_sha256_prefix":"3999ff487573f32c","entry":"select_best_resolution","repo":"deeplearnxmu/avg-llava","repo_kind":"official","path":"llava/mm_utils.py","file_url":"https://github.com/deeplearnxmu/avg-llava/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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3999ff487573f32c"}},{"code_sha256_prefix":"076c252c52cbb161","entry":"split_list","repo":"deeplearnxmu/avg-llava","repo_kind":"official","path":"llava/eval/model_vqa.py","file_url":"https://github.com/deeplearnxmu/avg-llava/blob/HEAD/llava/eval/model_vqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"076c252c52cbb161"}},{"code_sha256_prefix":"6c3e7a3c3b9dba43","entry":"greedy_search","repo":"deeplearnxmu/avg-llava","repo_kind":"official","path":"llava/generate_utils.py","file_url":"https://github.com/deeplearnxmu/avg-llava/blob/HEAD/llava/generate_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6c3e7a3c3b9dba43"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}