{"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/valley2-exploring-multimodal-models-with","title":"Valley2: Exploring Multimodal Models with Scalable Vision-Language Design","arxiv_id":"2501.05901","date":"2025-01-10","proceeding":null,"authors":["Ziheng Wu","Zhenghao Chen","Ruipu Luo","Can Zhang","Yuan Gao","Zhentao He","Xian Wang","Haoran Lin","Minghui Qiu"],"abstract":"Recently, vision-language models have made remarkable progress, demonstrating outstanding capabilities in various tasks such as image captioning and video understanding. We introduce Valley2, a novel multimodal large language model designed to enhance performance across all domains and extend the boundaries of practical applications in e-commerce and short video scenarios. Notably, Valley2 achieves state-of-the-art (SOTA) performance on e-commerce benchmarks, surpassing open-source models of similar size by a large margin (79.66 vs. 72.76). Additionally, Valley2 ranks second on the OpenCompass leaderboard among models with fewer than 10B parameters, with an impressive average score of 67.4. The code and model weights are open-sourced at https://github.com/bytedance/Valley.","url_abs":"https://arxiv.org/abs/2501.05901v2","url_pdf":"https://arxiv.org/pdf/2501.05901v2.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":"valley2-exploring-multimodal-models-with","repo_url":"https://github.com/bytedance/valley","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"multimodal-large-language-model","task_name":"Multimodal Large Language Model"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2501.05901","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.05901"}},"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/bytedance/valley","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":0,"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":"8519d8e6d16f76d6","entry":"b64_decode","repo":"bytedance/valley","repo_kind":"official","path":"valley/util/decode_img.py","file_url":"https://github.com/bytedance/valley/blob/HEAD/valley/util/decode_img.py","link_basis":"harvester_set","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":"8519d8e6d16f76d6"}},{"code_sha256_prefix":"5826cc219ebd0f66","entry":"check_model_config","repo":"bytedance/valley","repo_kind":"official","path":"valley2/valley_utils.py","file_url":"https://github.com/bytedance/valley/blob/HEAD/valley2/valley_utils.py","link_basis":"harvester_set","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":"5826cc219ebd0f66"}},{"code_sha256_prefix":"e1d6c2a78ced9904","entry":"collate_process_image_text","repo":"bytedance/valley","repo_kind":"official","path":"valley/util/data_util.py","file_url":"https://github.com/bytedance/valley/blob/HEAD/valley/util/data_util.py","link_basis":"harvester_set","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":"e1d6c2a78ced9904"}},{"code_sha256_prefix":"40f75b6a1d7442f3","entry":"collate_wrapper","repo":"bytedance/valley","repo_kind":"official","path":"valley/util/data_util.py","file_url":"https://github.com/bytedance/valley/blob/HEAD/valley/util/data_util.py","link_basis":"harvester_set","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":"40f75b6a1d7442f3"}},{"code_sha256_prefix":"bc264e58e84dcfbe","entry":"get_logger","repo":"bytedance/valley","repo_kind":"official","path":"valley/utils.py","file_url":"https://github.com/bytedance/valley/blob/HEAD/valley/utils.py","link_basis":"harvester_set","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":"bc264e58e84dcfbe"}},{"code_sha256_prefix":"54802dd67899555a","entry":"image_preprocess","repo":"bytedance/valley","repo_kind":"official","path":"valley/util/decode_img.py","file_url":"https://github.com/bytedance/valley/blob/HEAD/valley/util/decode_img.py","link_basis":"harvester_set","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":"54802dd67899555a"}},{"code_sha256_prefix":"bdb4a5432865c532","entry":"preprocess_multimodal","repo":"bytedance/valley","repo_kind":"official","path":"valley/util/data_util.py","file_url":"https://github.com/bytedance/valley/blob/HEAD/valley/util/data_util.py","link_basis":"harvester_set","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":"bdb4a5432865c532"}},{"code_sha256_prefix":"f9939a84b9a65279","entry":"violates_moderation","repo":"bytedance/valley","repo_kind":"official","path":"valley/utils.py","file_url":"https://github.com/bytedance/valley/blob/HEAD/valley/utils.py","link_basis":"harvester_set","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":"f9939a84b9a65279"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}