{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IWBYRN2ASLXKP6H7V375PJ5X4V","short_pith_number":"pith:IWBYRN2A","schema_version":"1.0","canonical_sha256":"458388b74092eea7f8ffaeffd7a7b7e55266a2aeb2963d1e0f1e15ceefe3d1fc","source":{"kind":"arxiv","id":"2311.01378","version":3},"attestation_state":"computed","paper":{"title":"Vision-Language Foundation Models as Effective Robot Imitators","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Simple fine-tuning adapts pre-trained vision-language models into robot policies that beat prior methods.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chilam Cheang, Cunjun Yu, Hanbo Zhang, Hang Li, Hongtao Wu, Huaping Liu, Jie Xu, Minghuan Liu, Tao Kong, Weinan Zhang, Xinghang Li, Ya Jing","submitted_at":"2023-11-02T16:34:33Z","abstract_excerpt":"Recent progress in vision language foundation models has shown their ability to understand multimodal data and resolve complicated vision language tasks, including robotics manipulation. We seek a straightforward way of making use of existing vision-language models (VLMs) with simple fine-tuning on robotics data. To this end, we derive a simple and novel vision-language manipulation framework, dubbed RoboFlamingo, built upon the open-source VLMs, OpenFlamingo. Unlike prior works, RoboFlamingo utilizes pre-trained VLMs for single-step vision-language comprehension, models sequential history inf"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2311.01378","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2023-11-02T16:34:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a46623a0809364e13041acd5187a238e16b787a3e7101eff9db09d46cb95d7f9","abstract_canon_sha256":"acf5b854e35077856f99fbbcc551f23d4efec5c2d3f5deccf242275df7a9dba8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:46.480027Z","signature_b64":"L9D4mjIB4siw7jWpM7R+Xd/KqkL3HDE5QJanziZc92qcLaS2grXF6HQQ/EGWMMlmlXiEKy98Ezz4ftEjus8FDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"458388b74092eea7f8ffaeffd7a7b7e55266a2aeb2963d1e0f1e15ceefe3d1fc","last_reissued_at":"2026-05-17T23:38:46.479380Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:46.479380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-Language Foundation Models as Effective Robot Imitators","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Simple fine-tuning adapts pre-trained vision-language models into robot policies that beat prior methods.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chilam Cheang, Cunjun Yu, Hanbo Zhang, Hang Li, Hongtao Wu, Huaping Liu, Jie Xu, Minghuan Liu, Tao Kong, Weinan Zhang, Xinghang Li, Ya Jing","submitted_at":"2023-11-02T16:34:33Z","abstract_excerpt":"Recent progress in vision language foundation models has shown their ability to understand multimodal data and resolve complicated vision language tasks, including robotics manipulation. We seek a straightforward way of making use of existing vision-language models (VLMs) with simple fine-tuning on robotics data. To this end, we derive a simple and novel vision-language manipulation framework, dubbed RoboFlamingo, built upon the open-source VLMs, OpenFlamingo. Unlike prior works, RoboFlamingo utilizes pre-trained VLMs for single-step vision-language comprehension, models sequential history inf"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By exceeding the state-of-the-art performance with a large margin on the tested benchmark, we show RoboFlamingo can be an effective and competitive alternative to adapt VLMs to robot control.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That modest fine-tuning on existing language-conditioned manipulation datasets is sufficient to transfer the general vision-language understanding of pre-trained VLMs into reliable sequential robot policies without catastrophic forgetting or domain shift.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"RoboFlamingo adapts open-source vision-language models for robot manipulation tasks via single-step comprehension plus an explicit policy head, outperforming prior methods on benchmarks with only light fine-tuning.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Simple fine-tuning adapts pre-trained vision-language models into robot policies that beat prior methods.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"91a85c646de6f8822037a18cc2a3b4a068bb69e07509d595515f345f2f48dba5"},"source":{"id":"2311.01378","kind":"arxiv","version":3},"verdict":{"id":"164d1108-8125-4063-9f30-d765cb47c30c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T21:40:52.339632Z","strongest_claim":"By exceeding the state-of-the-art performance with a large margin on the tested benchmark, we show RoboFlamingo can be an effective and competitive alternative to adapt VLMs to robot control.","one_line_summary":"RoboFlamingo adapts open-source vision-language models for robot manipulation tasks via single-step comprehension plus an explicit policy head, outperforming prior methods on benchmarks with only light fine-tuning.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That modest fine-tuning on existing language-conditioned manipulation datasets is sufficient to transfer the general vision-language understanding of pre-trained VLMs into reliable sequential robot policies without catastrophic forgetting or domain shift.","pith_extraction_headline":"Simple fine-tuning adapts pre-trained vision-language models into robot policies that beat prior methods."},"references":{"count":25,"sample":[{"doi":"","year":null,"title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","work_id":"037320f1-b0a9-4cbe-a639-bfb25409ce71","ref_index":1,"cited_arxiv_id":"2204.01691","is_internal_anchor":true},{"doi":"","year":null,"title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","work_id":"87bfa84a-e663-4165-806f-93ef439d88d0","ref_index":2,"cited_arxiv_id":"2308.01390","is_internal_anchor":true},{"doi":"","year":null,"title":"S., Purohit, S., Reynolds, L., Tow, J., Wang, B., and Weinbach, S","work_id":"168a55d5-675d-49cf-be47-a17ee8cd742e","ref_index":3,"cited_arxiv_id":"2204.06745","is_internal_anchor":true},{"doi":"","year":null,"title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","work_id":"ff438a8a-8003-4fae-9131-acd418b3597b","ref_index":4,"cited_arxiv_id":"2307.15818","is_internal_anchor":true},{"doi":"","year":1901,"title":"Language models are few-shot learners","work_id":"677093e0-2019-45af-8c52-d9b33dec7e3d","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":25,"snapshot_sha256":"176287bd0ea2afcf183ff6e753d1f38baffb67f66ee0f0a9630a812af836f494","internal_anchors":13},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b2d9565cc7de3aef309fec141a2ba2e069e8709d5cb7b522e9343be85d23e6d7"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.01378","created_at":"2026-05-17T23:38:46.479466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.01378v3","created_at":"2026-05-17T23:38:46.479466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01378","created_at":"2026-05-17T23:38:46.479466+00:00"},{"alias_kind":"pith_short_12","alias_value":"IWBYRN2ASLXK","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"IWBYRN2ASLXKP6H7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"IWBYRN2A","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":33,"internal_anchor_count":33,"sample":[{"citing_arxiv_id":"2405.14093","citing_title":"A Survey on Vision-Language-Action Models for Embodied AI","ref_index":104,"is_internal_anchor":true},{"citing_arxiv_id":"2505.03500","citing_title":"VLAs are Confined yet Capable of Generalizing to Novel Instructions","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2602.20200","citing_title":"Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20856","citing_title":"DISC: Decoupling Instruction from State-Conditioned Control via Policy Generation","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16241","citing_title":"Offline Semantic Guidance for Efficient Vision-Language-Action Policy Distillation","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17486","citing_title":"DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":114,"is_internal_anchor":true},{"citing_arxiv_id":"2402.15852","citing_title":"NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2402.10885","citing_title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","ref_index":74,"is_internal_anchor":true},{"citing_arxiv_id":"2412.14058","citing_title":"What Matters in Building Vision-Language-Action Models for Generalist Robots","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2511.15279","citing_title":"Look, Zoom, Understand: The Robotic Eyeball for Embodied Perception","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2505.15659","citing_title":"FLARE: Robot Learning with Implicit World Modeling","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2507.15493","citing_title":"GR-3 Technical Report","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2512.15840","citing_title":"Large Video Planner Enables Generalizable Robot Control","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2601.07060","citing_title":"PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2503.10631","citing_title":"HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2602.20231","citing_title":"UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Models","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07931","citing_title":"One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":266,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11665","citing_title":"Nautilus: From One Prompt to Plug-and-Play Robot Learning","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2412.14803","citing_title":"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations","ref_index":108,"is_internal_anchor":true},{"citing_arxiv_id":"2411.19650","citing_title":"CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07931","citing_title":"One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2410.06158","citing_title":"GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2506.21539","citing_title":"WorldVLA: Towards Autoregressive Action World Model","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IWBYRN2ASLXKP6H7V375PJ5X4V","json":"https://pith.science/pith/IWBYRN2ASLXKP6H7V375PJ5X4V.json","graph_json":"https://pith.science/api/pith-number/IWBYRN2ASLXKP6H7V375PJ5X4V/graph.json","events_json":"https://pith.science/api/pith-number/IWBYRN2ASLXKP6H7V375PJ5X4V/events.json","paper":"https://pith.science/paper/IWBYRN2A"},"agent_actions":{"view_html":"https://pith.science/pith/IWBYRN2ASLXKP6H7V375PJ5X4V","download_json":"https://pith.science/pith/IWBYRN2ASLXKP6H7V375PJ5X4V.json","view_paper":"https://pith.science/paper/IWBYRN2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.01378&json=true","fetch_graph":"https://pith.science/api/pith-number/IWBYRN2ASLXKP6H7V375PJ5X4V/graph.json","fetch_events":"https://pith.science/api/pith-number/IWBYRN2ASLXKP6H7V375PJ5X4V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IWBYRN2ASLXKP6H7V375PJ5X4V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IWBYRN2ASLXKP6H7V375PJ5X4V/action/storage_attestation","attest_author":"https://pith.science/pith/IWBYRN2ASLXKP6H7V375PJ5X4V/action/author_attestation","sign_citation":"https://pith.science/pith/IWBYRN2ASLXKP6H7V375PJ5X4V/action/citation_signature","submit_replication":"https://pith.science/pith/IWBYRN2ASLXKP6H7V375PJ5X4V/action/replication_record"}},"created_at":"2026-05-17T23:38:46.479466+00:00","updated_at":"2026-05-17T23:38:46.479466+00:00"}