{"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/worldgpt-empowering-llm-as-multimodal-world","title":"WorldGPT: Empowering LLM as Multimodal World Model","arxiv_id":"2404.18202","date":"2024-04-28","proceeding":null,"authors":["Zhiqi Ge","Hongzhe Huang","Mingze Zhou","Juncheng Li","Guoming Wang","Siliang Tang","Yueting Zhuang"],"abstract":"World models are progressively being employed across diverse fields, extending from basic environment simulation to complex scenario construction. However, existing models are mainly trained on domain-specific states and actions, and confined to single-modality state representations. In this paper, We introduce WorldGPT, a generalist world model built upon Multimodal Large Language Model (MLLM). WorldGPT acquires an understanding of world dynamics through analyzing millions of videos across various domains. To further enhance WorldGPT's capability in specialized scenarios and long-term tasks, we have integrated it with a novel cognitive architecture that combines memory offloading, knowledge retrieval, and context reflection. As for evaluation, we build WorldNet, a multimodal state transition prediction benchmark encompassing varied real-life scenarios. Conducting evaluations on WorldNet directly demonstrates WorldGPT's capability to accurately model state transition patterns, affirming its effectiveness in understanding and predicting the dynamics of complex scenarios. We further explore WorldGPT's emerging potential in serving as a world simulator, helping multimodal agents generalize to unfamiliar domains through efficiently synthesising multimodal instruction instances which are proved to be as reliable as authentic data for fine-tuning purposes. The project is available on \\url{https://github.com/DCDmllm/WorldGPT}.","url_abs":"https://arxiv.org/abs/2404.18202v2","url_pdf":"https://arxiv.org/pdf/2404.18202v2.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":"worldgpt-empowering-llm-as-multimodal-world","repo_url":"https://github.com/dcdmllm/worldgpt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"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":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.18202","atlas_url":"https://app.syntology.ai/?focus=2404.18202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18202"}},"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/dcdmllm/worldgpt","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran":3,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"9b4dff79d5e6102c","entry":"apply_rotary_pos_emb","repo":"dcdmllm/worldgpt","repo_kind":"official","path":"model/modeling_llama.py","file_url":"https://github.com/dcdmllm/worldgpt/blob/HEAD/model/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":"5fe66bcebddc1aab","entry":"collate","repo":"dcdmllm/worldgpt","repo_kind":"official","path":"batch_inference.py","file_url":"https://github.com/dcdmllm/worldgpt/blob/HEAD/batch_inference.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":"5fe66bcebddc1aab"}},{"code_sha256_prefix":"c06d403f220640c5","entry":"collate_decoder","repo":"dcdmllm/worldgpt","repo_kind":"official","path":"dataset/decoder_state_dataset.py","file_url":"https://github.com/dcdmllm/worldgpt/blob/HEAD/dataset/decoder_state_dataset.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":"c06d403f220640c5"}},{"code_sha256_prefix":"d220cbd62fb08952","entry":"l2_loss","repo":"dcdmllm/worldgpt","repo_kind":"official","path":"model/worldgpt.py","file_url":"https://github.com/dcdmllm/worldgpt/blob/HEAD/model/worldgpt.py","link_basis":"first_harvest_node","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":"d220cbd62fb08952"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"dcdmllm/worldgpt","repo_kind":"official","path":"model/modeling_llama.py","file_url":"https://github.com/dcdmllm/worldgpt/blob/HEAD/model/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"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}