{"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/vislinginstruct-elevating-zero-shot-learning","title":"VisLingInstruct: Elevating Zero-Shot Learning in Multi-Modal Language Models with Autonomous Instruction Optimization","arxiv_id":"2402.07398","date":"2024-02-12","proceeding":null,"authors":["Dongsheng Zhu","Xunzhu Tang","Weidong Han","Jinghui Lu","Yukun Zhao","Guoliang Xing","Junfeng Wang","Dawei Yin"],"abstract":"This paper presents VisLingInstruct, a novel approach to advancing Multi-Modal Language Models (MMLMs) in zero-shot learning. Current MMLMs show impressive zero-shot abilities in multi-modal tasks, but their performance depends heavily on the quality of instructions. VisLingInstruct tackles this by autonomously evaluating and optimizing instructional texts through In-Context Learning, improving the synergy between visual perception and linguistic expression in MMLMs. Alongside this instructional advancement, we have also optimized the visual feature extraction modules in MMLMs, further augmenting their responsiveness to textual content. Our comprehensive experiments on MMLMs, based on FlanT5 and Vicuna, show that VisLingInstruct significantly improves zero-shot performance in visual multi-modal tasks. Notably, it achieves a 13.1% and 9% increase in accuracy over the prior state-of-the-art on the TextVQA and HatefulMemes datasets. Our main code is available at https://github.com/Zhudongsheng75/VisLingInstruct.","url_abs":"https://arxiv.org/abs/2402.07398v3","url_pdf":"https://arxiv.org/pdf/2402.07398v3.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":"vislinginstruct-elevating-zero-shot-learning","repo_url":"https://github.com/zhudongsheng75/vislinginstruct","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":null,"task_name":"TextVQA"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.07398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07398"}},"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/zhudongsheng75/vislinginstruct","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran_violates":1,"ran_draft_wrong":2,"ran":3,"unverified":4},"by_repo_kind":{"official":{"samples":11,"ran":7,"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":11,"samples":[{"code_sha256_prefix":"9b4dff79d5e6102c","entry":"apply_rotary_pos_emb","repo":"zhudongsheng75/vislinginstruct","repo_kind":"official","path":"vislinginstruct/models/modeling_llama.py","file_url":"https://github.com/zhudongsheng75/vislinginstruct/blob/HEAD/vislinginstruct/models/modeling_llama.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9b4dff79d5e6102c"}},{"code_sha256_prefix":"4cb732f513d69dfd","entry":"disabled_train","repo":"zhudongsheng75/vislinginstruct","repo_kind":"official","path":"vislinginstruct/models/blip2.py","file_url":"https://github.com/zhudongsheng75/vislinginstruct/blob/HEAD/vislinginstruct/models/blip2.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4cb732f513d69dfd"}},{"code_sha256_prefix":"c6ec173f19f5c34d","entry":"interpolate_pos_embed","repo":"zhudongsheng75/vislinginstruct","repo_kind":"official","path":"vislinginstruct/models/vit.py","file_url":"https://github.com/zhudongsheng75/vislinginstruct/blob/HEAD/vislinginstruct/models/vit.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c6ec173f19f5c34d"}},{"code_sha256_prefix":"98589643273920ba","entry":"main_process","repo":"zhudongsheng75/vislinginstruct","repo_kind":"official","path":"vislinginstruct/common/dist_utils.py","file_url":"https://github.com/zhudongsheng75/vislinginstruct/blob/HEAD/vislinginstruct/common/dist_utils.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":"98589643273920ba"}},{"code_sha256_prefix":"791c72070c0b1cfb","entry":"node_to_dict","repo":"zhudongsheng75/vislinginstruct","repo_kind":"official","path":"vislinginstruct/common/config.py","file_url":"https://github.com/zhudongsheng75/vislinginstruct/blob/HEAD/vislinginstruct/common/config.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":"791c72070c0b1cfb"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"zhudongsheng75/vislinginstruct","repo_kind":"official","path":"vislinginstruct/models/modeling_llama.py","file_url":"https://github.com/zhudongsheng75/vislinginstruct/blob/HEAD/vislinginstruct/models/modeling_llama.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":"b99eea6376d1e212"}},{"code_sha256_prefix":"cb33571427334815","entry":"tile","repo":"zhudongsheng75/vislinginstruct","repo_kind":"official","path":"vislinginstruct/models/base_model.py","file_url":"https://github.com/zhudongsheng75/vislinginstruct/blob/HEAD/vislinginstruct/models/base_model.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":"cb33571427334815"}},{"code_sha256_prefix":"0ec9fc2025c16f65","entry":"all_gather_with_grad","repo":"zhudongsheng75/vislinginstruct","repo_kind":"official","path":"vislinginstruct/models/base_model.py","file_url":"https://github.com/zhudongsheng75/vislinginstruct/blob/HEAD/vislinginstruct/models/base_model.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":"0ec9fc2025c16f65"}},{"code_sha256_prefix":"5ff657c46012729d","entry":"create_eva_vit_g","repo":"zhudongsheng75/vislinginstruct","repo_kind":"official","path":"vislinginstruct/models/eva_vit.py","file_url":"https://github.com/zhudongsheng75/vislinginstruct/blob/HEAD/vislinginstruct/models/eva_vit.py","link_basis":"first_harvest_node","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":"5ff657c46012729d"}},{"code_sha256_prefix":"643539116e049080","entry":"download_cached_file","repo":"zhudongsheng75/vislinginstruct","repo_kind":"official","path":"vislinginstruct/common/dist_utils.py","file_url":"https://github.com/zhudongsheng75/vislinginstruct/blob/HEAD/vislinginstruct/common/dist_utils.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":"643539116e049080"}},{"code_sha256_prefix":"bfbc7746415f3426","entry":"load_tf_weights_in_t5","repo":"zhudongsheng75/vislinginstruct","repo_kind":"official","path":"vislinginstruct/models/modeling_t5.py","file_url":"https://github.com/zhudongsheng75/vislinginstruct/blob/HEAD/vislinginstruct/models/modeling_t5.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":"bfbc7746415f3426"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}