{"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/grounded-3d-llm-with-referent-tokens","title":"Grounded 3D-LLM with Referent Tokens","arxiv_id":"2405.10370","date":"2024-05-16","proceeding":null,"authors":["Yilun Chen","Shuai Yang","Haifeng Huang","Tai Wang","Runsen Xu","Ruiyuan Lyu","Dahua Lin","Jiangmiao Pang"],"abstract":"Prior studies on 3D scene understanding have primarily developed specialized models for specific tasks or required task-specific fine-tuning. In this study, we propose Grounded 3D-LLM, which explores the potential of 3D large multi-modal models (3D LMMs) to consolidate various 3D vision tasks within a unified generative framework. The model uses scene referent tokens as special noun phrases to reference 3D scenes, enabling it to handle sequences that interleave 3D and textual data. Per-task instruction-following templates are employed to ensure natural and diversity in translating 3D vision tasks into language formats. To facilitate the use of referent tokens in subsequent language modeling, we provide a large-scale, automatically curated grounded scene-text dataset with over 1 million phrase-to-region correspondences and introduce Contrastive Language-Scene Pre-training (CLASP) to perform phrase-level scene-text alignment using this data. Our comprehensive evaluation covers open-ended tasks like dense captioning and 3D question answering, alongside close-ended tasks such as object detection and language grounding. Experiments across multiple 3D benchmarks reveal the leading performance and the broad applicability of Grounded 3D-LLM. Code and datasets are available at the https://groundedscenellm.github.io/grounded_3d-llm.github.io.","url_abs":"https://arxiv.org/abs/2405.10370v2","url_pdf":"https://arxiv.org/pdf/2405.10370v2.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":"grounded-3d-llm-with-referent-tokens","repo_url":"https://github.com/OpenRobotLab/Grounded_3D-LLM","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"dense-captioning","task_name":"Dense Captioning"},{"task_slug":"diversity","task_name":"Diversity"},{"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":"object-detection","task_name":"Object Detection"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.10370","atlas_url":"https://app.syntology.ai/?focus=2405.10370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10370"}},"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/OpenRobotLab/Grounded_3D-LLM","reach":{"status":"ok"}}],"summary":{"ran_fixture":2,"ran":6,"ran_draft_wrong":1,"unverified":8},"by_repo_kind":{"official":{"samples":17,"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":17,"samples":[{"code_sha256_prefix":"30d7eec482ebf6b1","entry":"repeat_kv","repo":"OpenRobotLab/Grounded_3D-LLM","repo_kind":"official","path":"models/LLM/modeling_llama.py","file_url":"https://github.com/OpenRobotLab/Grounded_3D-LLM/blob/HEAD/models/LLM/modeling_llama.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"30d7eec482ebf6b1"}},{"code_sha256_prefix":"d61c483a3c2b3156","entry":"apply_rotary_pos_emb","repo":"OpenRobotLab/Grounded_3D-LLM","repo_kind":"official","path":"models/LLM/modeling_llama.py","file_url":"https://github.com/OpenRobotLab/Grounded_3D-LLM/blob/HEAD/models/LLM/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":"d61c483a3c2b3156"}},{"code_sha256_prefix":"af45d6b0d475f902","entry":"extract_decoder_hidden_states","repo":"OpenRobotLab/Grounded_3D-LLM","repo_kind":"official","path":"models/LLM/llama_utils.py","file_url":"https://github.com/OpenRobotLab/Grounded_3D-LLM/blob/HEAD/models/LLM/llama_utils.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":"af45d6b0d475f902"}},{"code_sha256_prefix":"fe938788e6c1b91e","entry":"extract_numbers_and_string","repo":"OpenRobotLab/Grounded_3D-LLM","repo_kind":"official","path":"models/metrics/evaluate_LLM.py","file_url":"https://github.com/OpenRobotLab/Grounded_3D-LLM/blob/HEAD/models/metrics/evaluate_LLM.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":"fe938788e6c1b91e"}},{"code_sha256_prefix":"982eff1f79a70a95","entry":"get_batch_aabb_pair_ious","repo":"OpenRobotLab/Grounded_3D-LLM","repo_kind":"official","path":"models/metrics/evaluate_LLM.py","file_url":"https://github.com/OpenRobotLab/Grounded_3D-LLM/blob/HEAD/models/metrics/evaluate_LLM.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":"982eff1f79a70a95"}},{"code_sha256_prefix":"98cb6f5c94e2ed6a","entry":"get_loss_for_each_type","repo":"OpenRobotLab/Grounded_3D-LLM","repo_kind":"official","path":"models/LLM/llama_utils.py","file_url":"https://github.com/OpenRobotLab/Grounded_3D-LLM/blob/HEAD/models/LLM/llama_utils.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":"98cb6f5c94e2ed6a"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"OpenRobotLab/Grounded_3D-LLM","repo_kind":"official","path":"models/LLM/modeling_llama.py","file_url":"https://github.com/OpenRobotLab/Grounded_3D-LLM/blob/HEAD/models/LLM/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":"d8f1ec58fa91ba5f","entry":"simple_ratio","repo":"OpenRobotLab/Grounded_3D-LLM","repo_kind":"official","path":"models/LLM/scanqa_score.py","file_url":"https://github.com/OpenRobotLab/Grounded_3D-LLM/blob/HEAD/models/LLM/scanqa_score.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":"d8f1ec58fa91ba5f"}},{"code_sha256_prefix":"d4d10e9d1f354600","entry":"smooth_l1","repo":"OpenRobotLab/Grounded_3D-LLM","repo_kind":"official","path":"models/matcher.py","file_url":"https://github.com/OpenRobotLab/Grounded_3D-LLM/blob/HEAD/models/matcher.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":"d4d10e9d1f354600"}},{"code_sha256_prefix":"bc2cb481a75c370d","entry":"batch_dice_loss","repo":"OpenRobotLab/Grounded_3D-LLM","repo_kind":"official","path":"models/matcher.py","file_url":"https://github.com/OpenRobotLab/Grounded_3D-LLM/blob/HEAD/models/matcher.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":"bc2cb481a75c370d"}},{"code_sha256_prefix":"4854fff95b83b510","entry":"binary_focal_loss_cost","repo":"OpenRobotLab/Grounded_3D-LLM","repo_kind":"official","path":"models/matcher.py","file_url":"https://github.com/OpenRobotLab/Grounded_3D-LLM/blob/HEAD/models/matcher.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":"4854fff95b83b510"}},{"code_sha256_prefix":"2dcb8123d89bb1ff","entry":"calculate_uncertainty","repo":"OpenRobotLab/Grounded_3D-LLM","repo_kind":"official","path":"models/criterion.py","file_url":"https://github.com/OpenRobotLab/Grounded_3D-LLM/blob/HEAD/models/criterion.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":"2dcb8123d89bb1ff"}},{"code_sha256_prefix":"89f75e54ff128be0","entry":"dice_loss","repo":"OpenRobotLab/Grounded_3D-LLM","repo_kind":"official","path":"models/criterion.py","file_url":"https://github.com/OpenRobotLab/Grounded_3D-LLM/blob/HEAD/models/criterion.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":"89f75e54ff128be0"}},{"code_sha256_prefix":"f16e9fe96aedf28e","entry":"eval_llm_iou_score","repo":"OpenRobotLab/Grounded_3D-LLM","repo_kind":"official","path":"models/metrics/evaluate_LLM.py","file_url":"https://github.com/OpenRobotLab/Grounded_3D-LLM/blob/HEAD/models/metrics/evaluate_LLM.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":"f16e9fe96aedf28e"}},{"code_sha256_prefix":"a1ff41c753bffe5d","entry":"get_lemma","repo":"OpenRobotLab/Grounded_3D-LLM","repo_kind":"official","path":"models/LLM/scanqa_score.py","file_url":"https://github.com/OpenRobotLab/Grounded_3D-LLM/blob/HEAD/models/LLM/scanqa_score.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":"a1ff41c753bffe5d"}},{"code_sha256_prefix":"d0c61e8dba511aa3","entry":"sigmoid_ce_loss","repo":"OpenRobotLab/Grounded_3D-LLM","repo_kind":"official","path":"models/criterion.py","file_url":"https://github.com/OpenRobotLab/Grounded_3D-LLM/blob/HEAD/models/criterion.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":"d0c61e8dba511aa3"}},{"code_sha256_prefix":"115badbfb8522aa6","entry":"tokens_unigram_f_value","repo":"OpenRobotLab/Grounded_3D-LLM","repo_kind":"official","path":"models/LLM/scanqa_score.py","file_url":"https://github.com/OpenRobotLab/Grounded_3D-LLM/blob/HEAD/models/LLM/scanqa_score.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":"115badbfb8522aa6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}