{"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/dreamvla-a-vision-language-action-model-1","title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","arxiv_id":"2507.04447","date":"2025-07-06","proceeding":null,"authors":["Wenyao Zhang","Hongsi Liu","Zekun Qi","Yunnan Wang","Xinqiang Yu","Jiazhao Zhang","Runpei Dong","JiaWei He","He Wang","Zhizheng Zhang","Li Yi","Wenjun Zeng","Xin Jin"],"abstract":"Recent advances in vision-language-action (VLA) models have shown promise in integrating image generation with action prediction to improve generalization and reasoning in robot manipulation. However, existing methods are limited to challenging image-based forecasting, which suffers from redundant information and lacks comprehensive and critical world knowledge, including dynamic, spatial and semantic information. To address these limitations, we propose DreamVLA, a novel VLA framework that integrates comprehensive world knowledge forecasting to enable inverse dynamics modeling, thereby establishing a perception-prediction-action loop for manipulation tasks. Specifically, DreamVLA introduces a dynamic-region-guided world knowledge prediction, integrated with the spatial and semantic cues, which provide compact yet comprehensive representations for action planning. This design aligns with how humans interact with the world by first forming abstract multimodal reasoning chains before acting. To mitigate interference among the dynamic, spatial and semantic information during training, we adopt a block-wise structured attention mechanism that masks their mutual attention, preventing information leakage and keeping each representation clean and disentangled. Moreover, to model the conditional distribution over future actions, we employ a diffusion-based transformer that disentangles action representations from shared latent features. Extensive experiments on both real-world and simulation environments demonstrate that DreamVLA achieves 76.7% success rate on real robot tasks and 4.44 average length on the CALVIN ABC-D benchmarks.","url_abs":"https://arxiv.org/abs/2507.04447v2","url_pdf":"https://arxiv.org/pdf/2507.04447v2.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":"dreamvla-a-vision-language-action-model-1","repo_url":"https://github.com/Zhangwenyao1/DreamVLA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"multimodal-reasoning","task_name":"Multimodal Reasoning"},{"task_slug":"robot-manipulation","task_name":"Robot Manipulation"},{"task_slug":"vision-language-action","task_name":"Vision-Language-Action"},{"task_slug":"world-knowledge","task_name":"World Knowledge"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/robot-manipulation-on-calvin","task":"Robot Manipulation","dataset":"CALVIN","model":"DreamVLA","rank_in_archive_order":1,"of":19,"metrics":{"avg. sequence length (D to D)":"4.44"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2507.04447","atlas_url":"https://app.syntology.ai/?focus=2507.04447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.04447"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/Zhangwenyao1/DreamVLA","reach":null}],"summary":{"ran_violates":1,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"f8dd22c2d14d4521","entry":"generate_attention_mask","repo":"Zhangwenyao1/DreamVLA","repo_kind":"official","path":"models/dreamvla_model.py","file_url":"https://github.com/Zhangwenyao1/DreamVLA/blob/HEAD/models/dreamvla_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f8dd22c2d14d4521"}},{"code_sha256_prefix":"5c8ea92d43ead77d","entry":"get_1d_sincos_pos_embed_from_grid","repo":"Zhangwenyao1/DreamVLA","repo_kind":"official","path":"models/dreamvla_model.py","file_url":"https://github.com/Zhangwenyao1/DreamVLA/blob/HEAD/models/dreamvla_model.py","link_basis":"first_harvest_node","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":"5c8ea92d43ead77d"}},{"code_sha256_prefix":"2884deadbb637c3e","entry":"get_2d_sincos_pos_embed_from_grid","repo":"Zhangwenyao1/DreamVLA","repo_kind":"official","path":"models/dreamvla_model.py","file_url":"https://github.com/Zhangwenyao1/DreamVLA/blob/HEAD/models/dreamvla_model.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":"2884deadbb637c3e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}