{"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/robin3d-improving-3d-large-language-model-via","title":"Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning","arxiv_id":"2410.00255","date":"2024-09-30","proceeding":null,"authors":["Weitai Kang","Haifeng Huang","Yuzhang Shang","Mubarak Shah","Yan Yan"],"abstract":"Recent advancements in 3D Large Language Models (3DLLMs) have highlighted their potential in building general-purpose agents in the 3D real world, yet challenges remain due to the lack of high-quality robust instruction-following data, leading to limited discriminative power and generalization of 3DLLMs. In this paper, we introduce Robin3D, a powerful 3DLLM trained on large-scale instruction-following data generated by our novel data engine, Robust Instruction Generation (RIG) engine. RIG generates two key instruction data: 1) the Adversarial Instruction-following data, which features mixed negative and positive samples to enhance the model's discriminative understanding. 2) the Diverse Instruction-following data, which contains various instruction styles to enhance model's generalization. As a result, we construct 1 million instruction-following data, consisting of 344K Adversarial samples, 508K Diverse samples, and 165K benchmark training set samples. To better handle these complex instructions, Robin3D first incorporates Relation-Augmented Projector to enhance spatial understanding, and then strengthens the object referring and grounding ability through ID-Feature Bonding. Robin3D consistently outperforms previous methods across five widely-used 3D multimodal learning benchmarks, without the need for task-specific fine-tuning. Notably, we achieve a 7.8\\% improvement in the grounding task (Multi3DRefer) and a 6.9\\% improvement in the captioning task (Scan2Cap).","url_abs":"https://arxiv.org/abs/2410.00255v1","url_pdf":"https://arxiv.org/pdf/2410.00255v1.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":"robin3d-improving-3d-large-language-model-via","repo_url":"https://github.com/weitaikang/robin3d","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"},{"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"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.00255","atlas_url":"https://app.syntology.ai/?focus=2410.00255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00255"}},"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/weitaikang/robin3d","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":3,"ran":5},"by_repo_kind":{"official":{"samples":9,"ran":9,"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":"30d7eec482ebf6b1","entry":"repeat_kv","repo":"weitaikang/robin3d","repo_kind":"official","path":"models/modeling_llama.py","file_url":"https://github.com/weitaikang/robin3d/blob/HEAD/models/modeling_llama.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"30d7eec482ebf6b1"}},{"code_sha256_prefix":"bac65c3dafaec040","entry":"apply_rotary_pos_emb","repo":"weitaikang/robin3d","repo_kind":"official","path":"models/modeling_llama.py","file_url":"https://github.com/weitaikang/robin3d/blob/HEAD/models/modeling_llama.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bac65c3dafaec040"}},{"code_sha256_prefix":"4e0f1a685475cdef","entry":"clean_sentence","repo":"weitaikang/robin3d","repo_kind":"official","path":"analyze_data.py","file_url":"https://github.com/weitaikang/robin3d/blob/HEAD/analyze_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e0f1a685475cdef"}},{"code_sha256_prefix":"cda0cda020ca6dee","entry":"get_caption","repo":"weitaikang/robin3d","repo_kind":"official","path":"preprocess/prepare_scannet_region_caption_annos.py","file_url":"https://github.com/weitaikang/robin3d/blob/HEAD/preprocess/prepare_scannet_region_caption_annos.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cda0cda020ca6dee"}},{"code_sha256_prefix":"891b8ebab395921f","entry":"get_clones","repo":"weitaikang/robin3d","repo_kind":"official","path":"models/helpers.py","file_url":"https://github.com/weitaikang/robin3d/blob/HEAD/models/helpers.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"891b8ebab395921f"}},{"code_sha256_prefix":"3f8b2fc0609a5184","entry":"nclamp","repo":"weitaikang/robin3d","repo_kind":"official","path":"models/chat3d.py","file_url":"https://github.com/weitaikang/robin3d/blob/HEAD/models/chat3d.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3f8b2fc0609a5184"}},{"code_sha256_prefix":"3895c5e4b8839cf6","entry":"recover_caption","repo":"weitaikang/robin3d","repo_kind":"official","path":"preprocess/prepare_scannet_region_caption_annos.py","file_url":"https://github.com/weitaikang/robin3d/blob/HEAD/preprocess/prepare_scannet_region_caption_annos.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3895c5e4b8839cf6"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"weitaikang/robin3d","repo_kind":"official","path":"models/modeling_llama.py","file_url":"https://github.com/weitaikang/robin3d/blob/HEAD/models/modeling_llama.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b99eea6376d1e212"}},{"code_sha256_prefix":"8ea16420707b36f4","entry":"update_caption","repo":"weitaikang/robin3d","repo_kind":"official","path":"preprocess/prepare_scannet_region_caption_annos.py","file_url":"https://github.com/weitaikang/robin3d/blob/HEAD/preprocess/prepare_scannet_region_caption_annos.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ea16420707b36f4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}