{"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/cognitive-visual-language-mapper-advancing","title":"Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment","arxiv_id":"2402.13561","date":"2024-02-21","proceeding":null,"authors":["Yunxin Li","Xinyu Chen","Baotian Hu","Haoyuan Shi","Min Zhang"],"abstract":"Evaluating and Rethinking the current landscape of Large Multimodal Models (LMMs), we observe that widely-used visual-language projection approaches (e.g., Q-former or MLP) focus on the alignment of image-text descriptions yet ignore the visual knowledge-dimension alignment, i.e., connecting visuals to their relevant knowledge. Visual knowledge plays a significant role in analyzing, inferring, and interpreting information from visuals, helping improve the accuracy of answers to knowledge-based visual questions. In this paper, we mainly explore improving LMMs with visual-language knowledge alignment, especially aimed at challenging knowledge-based visual question answering (VQA). To this end, we present a Cognitive Visual-Language Mapper (CVLM), which contains a pretrained Visual Knowledge Aligner (VKA) and a Fine-grained Knowledge Adapter (FKA) used in the multimodal instruction tuning stage. Specifically, we design the VKA based on the interaction between a small language model and a visual encoder, training it on collected image-knowledge pairs to achieve visual knowledge acquisition and projection. FKA is employed to distill the fine-grained visual knowledge of an image and inject it into Large Language Models (LLMs). We conduct extensive experiments on knowledge-based VQA benchmarks and experimental results show that CVLM significantly improves the performance of LMMs on knowledge-based VQA (average gain by 5.0%). Ablation studies also verify the effectiveness of VKA and FKA, respectively. The codes are available at https://github.com/HITsz-TMG/Cognitive-Visual-Language-Mapper","url_abs":"https://arxiv.org/abs/2402.13561v2","url_pdf":"https://arxiv.org/pdf/2402.13561v2.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":"cognitive-visual-language-mapper-advancing","repo_url":"https://github.com/hitsz-tmg/cognitive-visual-language-mapper","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"small-language-model","task_name":"Small Language Model"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.13561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13561"}},"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/hitsz-tmg/cognitive-visual-language-mapper","reach":{"status":"ok"}}],"summary":{"ran":4,"ran_draft_wrong":1,"ran_violates":1,"unverified":4},"by_repo_kind":{"official":{"samples":10,"ran":6,"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":10,"samples":[{"code_sha256_prefix":"77e8a3ac46f3afec","entry":"get_2d_sincos_pos_embed","repo":"hitsz-tmg/cognitive-visual-language-mapper","repo_kind":"official","path":"Qwen/Qwen_VL/visual.py","file_url":"https://github.com/hitsz-tmg/cognitive-visual-language-mapper/blob/HEAD/Qwen/Qwen_VL/visual.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"77e8a3ac46f3afec"}},{"code_sha256_prefix":"50c4398a8645438a","entry":"get_abs_pos","repo":"hitsz-tmg/cognitive-visual-language-mapper","repo_kind":"official","path":"Qwen/Qwen_VL/visual.py","file_url":"https://github.com/hitsz-tmg/cognitive-visual-language-mapper/blob/HEAD/Qwen/Qwen_VL/visual.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"50c4398a8645438a"}},{"code_sha256_prefix":"fb48214e8ea84c17","entry":"get_eval","repo":"hitsz-tmg/cognitive-visual-language-mapper","repo_kind":"official","path":"LLaVA/llava/eval/eval_gpt_review_visual.py","file_url":"https://github.com/hitsz-tmg/cognitive-visual-language-mapper/blob/HEAD/LLaVA/llava/eval/eval_gpt_review_visual.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fb48214e8ea84c17"}},{"code_sha256_prefix":"1586b639a5abd0b0","entry":"init_to_zero","repo":"hitsz-tmg/cognitive-visual-language-mapper","repo_kind":"official","path":"LLaVA/llava/model/language_model/mpt/flash_attn_triton.py","file_url":"https://github.com/hitsz-tmg/cognitive-visual-language-mapper/blob/HEAD/LLaVA/llava/model/language_model/mpt/flash_attn_triton.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1586b639a5abd0b0"}},{"code_sha256_prefix":"763f6fe20bd52fbb","entry":"parse_score","repo":"hitsz-tmg/cognitive-visual-language-mapper","repo_kind":"official","path":"LLaVA/llava/eval/eval_gpt_review_visual.py","file_url":"https://github.com/hitsz-tmg/cognitive-visual-language-mapper/blob/HEAD/LLaVA/llava/eval/eval_gpt_review_visual.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"763f6fe20bd52fbb"}},{"code_sha256_prefix":"9770697ce0d31740","entry":"preprocess","repo":"hitsz-tmg/cognitive-visual-language-mapper","repo_kind":"official","path":"Qwen/finetune.py","file_url":"https://github.com/hitsz-tmg/cognitive-visual-language-mapper/blob/HEAD/Qwen/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9770697ce0d31740"}},{"code_sha256_prefix":"69a085d27f83db2a","entry":"flash_attn_fn","repo":"hitsz-tmg/cognitive-visual-language-mapper","repo_kind":"official","path":"LLaVA/llava/model/language_model/mpt/attention.py","file_url":"https://github.com/hitsz-tmg/cognitive-visual-language-mapper/blob/HEAD/LLaVA/llava/model/language_model/mpt/attention.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"69a085d27f83db2a"}},{"code_sha256_prefix":"2884deadbb637c3e","entry":"get_2d_sincos_pos_embed_from_grid","repo":"hitsz-tmg/cognitive-visual-language-mapper","repo_kind":"official","path":"Qwen/Qwen_VL/visual.py","file_url":"https://github.com/hitsz-tmg/cognitive-visual-language-mapper/blob/HEAD/Qwen/Qwen_VL/visual.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2884deadbb637c3e"}},{"code_sha256_prefix":"cd623891235b1d02","entry":"scaled_multihead_dot_product_attention","repo":"hitsz-tmg/cognitive-visual-language-mapper","repo_kind":"official","path":"LLaVA/llava/model/language_model/mpt/attention.py","file_url":"https://github.com/hitsz-tmg/cognitive-visual-language-mapper/blob/HEAD/LLaVA/llava/model/language_model/mpt/attention.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cd623891235b1d02"}},{"code_sha256_prefix":"a27f1a3818430d86","entry":"triton_flash_attn_fn","repo":"hitsz-tmg/cognitive-visual-language-mapper","repo_kind":"official","path":"LLaVA/llava/model/language_model/mpt/attention.py","file_url":"https://github.com/hitsz-tmg/cognitive-visual-language-mapper/blob/HEAD/LLaVA/llava/model/language_model/mpt/attention.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a27f1a3818430d86"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}