{"work":{"id":"f7c5ce10-8364-4fbe-964f-2802b81c3a98","openalex_id":"https://openalex.org/W4409015946","doi":"10.48550/arxiv.2503.20020","arxiv_id":"2503.20020","raw_key":null,"title":"Gemini Robotics: Bringing AI into the Physical World","authors":null,"authors_text":"Gemini Robotics Team, Saminda Abeyruwan, Joshua Ainslie, Jean-Baptiste Alayrac, Montserrat Gonzalez Arenas, Travis Armstrong","year":2025,"venue":"cs.RO","abstract":"Recent advancements in large multimodal models have led to the emergence of remarkable generalist capabilities in digital domains, yet their translation to physical agents such as robots remains a significant challenge. This report introduces a new family of AI models purposefully designed for robotics and built upon the foundation of Gemini 2.0. We present Gemini Robotics, an advanced Vision-Language-Action (VLA) generalist model capable of directly controlling robots. Gemini Robotics executes smooth and reactive movements to tackle a wide range of complex manipulation tasks while also being robust to variations in object types and positions, handling unseen environments as well as following diverse, open vocabulary instructions. We show that with additional fine-tuning, Gemini Robotics can be specialized to new capabilities including solving long-horizon, highly dexterous tasks, learning new short-horizon tasks from as few as 100 demonstrations and adapting to completely novel robot embodiments. This is made possible because Gemini Robotics builds on top of the Gemini Robotics-ER model, the second model we introduce in this work. Gemini Robotics-ER (Embodied Reasoning) extends Gemini's multimodal reasoning capabilities into the physical world, with enhanced spatial and temporal understanding. This enables capabilities relevant to robotics including object detection, pointing, trajectory and grasp prediction, as well as multi-view correspondence and 3D bounding box predictions. We show how this novel combination can support a variety of robotics applications. We also discuss and address important safety considerations related to this new class of robotics foundation models. The Gemini Robotics family marks a substantial step towards developing general-purpose robots that realizes AI's potential in the physical world.","external_url":"https://arxiv.org/abs/2503.20020","cited_by_count":5,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2503.20020","created_at":"2026-05-09T06:05:35.143667+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"Gemini Robotics: Bringing AI into the Physical World","render_title":"Gemini Robotics: Bringing AI into the Physical World"},"hub":{"state":{"work_id":"f7c5ce10-8364-4fbe-964f-2802b81c3a98","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":122,"external_cited_by_count":5,"distinct_field_count":6,"first_pith_cited_at":"2025-02-09T11:25:56+00:00","last_pith_cited_at":"2026-07-09T16:15:43+00:00","author_build_status":"needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-20T09:59:21.834730+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"background","n":29},{"context_role":"dataset","n":4},{"context_role":"baseline","n":1}],"polarity_counts":[{"context_polarity":"background","n":28},{"context_polarity":"use_dataset","n":4},{"context_polarity":"baseline","n":1},{"context_polarity":"unclear","n":1}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"Gemini Robotics: Bringing AI into the Physical World","claims":[{"claim_text":"Recent advancements in large multimodal models have led to the emergence of remarkable generalist capabilities in digital domains, yet their translation to physical agents such as robots remains a significant challenge. This report introduces a new family of AI models purposefully designed for robotics and built upon the foundation of Gemini 2.0. We present Gemini Robotics, an advanced Vision-Language-Action (VLA) generalist model capable of directly controlling robots. Gemini Robotics executes smooth and reactive movements to tackle a wide range of complex manipulation tasks while also being ","claim_type":"abstract","evidence_strength":"source_metadata"},{"claim_text":"Gemini: a family of highly capable multimodal models.arXiv preprint arXiv:2312.11805, 2023. [122] Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.arXiv preprint arXiv:2403.05530, 2024. [123] Gemini Robotics Team, Saminda Abeyruwan, Joshua Ainslie, Jean-Baptiste Alayrac, Montser- rat Gonzalez Arenas, Travis Armstrong,","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"extend the scaling laws [19, 20] observed in vision and language domains to the embodied setting, collecting large-scale embodied datasets and training generalist agents end-to-end on top of vision-language foundation models [21, 22, 23]. These diverse approaches have led to a rapid proliferation of VLA models in robotic manipulation [24, 25], navigation [26, 27], and autonomous driving [28, 29, 30], demonstrating promising capabilities in multitask learning [31], long-horizon task completion [2","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"9 64.3/73.1◦ Pointing & Counting CountBench [49] 91.0 91.0 91.097.391.8 96.3 FSC-147 [2]↓ 22.0 28.0 24.512.117.9 13.6 Point-Bench [14] 33.8 41.8 ∗ 62.7∗ 85.5∗ 74.9 76.5 2D & 3D Spatial Understanding BLINK [23] 63.4 69.6 70.677.172.1 74.3 MMSIBench (circular) [83] 17.2 22.3 17.6 25.4 11.7 25.8 RefSpatialBench [94] 21.7 28.2 ∗ 33.6∗ 65.5∗ 58.8 56.3 ERQA [63] 49.8 60.0 ∗ 56.0∗ 70.5∗ 47.0 58.8 DA-2K [82] 68.2 78.6 76.5 82.1 85.3 90.7 CV-Bench [65] 79.3 84.6 85.992.084.9 88.0 Document & Chart Underst","claim_type":"dataset","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"• OCR, Chart & Document: OCRBench [ 31], ChartQAPro [ 35], ChartMuseum [ 45], MMLongBench-Doc [34]; •Visual Grounding: RefCOCO-avg (val) [25], TreeBench [54], Ref-L4 [6]; •GUI Agents: OSWorld [62], Android World [38], WebV oyager Some [18], Webquest-QA [56]; •Coding: Design2Code [43], Flame-React-Eval [1]; • Spatial Reco & Reasoning: OminiSpatial [24], CV-Bench [51], ERQA [49], All-Angles Bench [65]; • Video Understanding: VideoMME [ 10], MMVU [ 71], VideoMMMU [ 22], LVBench [ 58], MotionBench [","claim_type":"dataset","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"5-VL performance on public video benchmarks compared to previous models. For all benchmarks, higher numbers are better. The evaluation frame rates are 2 FPS for MotionBench, MVBench, TOMATO, and TVBench, 3 FPS for Dream-1K, and 1 FPS for all other datasets. Capability Benchmark Seed OpenAI Claude UI-TARS Kimi Qwen 2.5 1.5-VL CUA [98] 3.7 Sonnet [6] 1.5 [116] VL-A3B [130] VL 72B [7] GUI Grounding ScreenSpot-V2 [149] 95.2 87.9 87 .6 94 .2 92.8 - ScreenSpot-Pro [72] 60.9 23.4 27 .7 61.6 34.5 43 .6 ","claim_type":"baseline","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"[66] DJ Strouse, Kevin McKee, Matt Botvinick, Edward Hughes, and Richard Everett. Collaborat- ing with humans without human data. Advances in Neural Information Processing Systems, 34:14502-14515, 2021. [67] Zhenggang Tang, Chao Yu, Boyuan Chen, Huazhe Xu, Xiaolong Wang, Fei Fang, Simon Du, Yu Wang, and Yi Wu. Discovering diverse multi-agent strategic behavior via reward randomization. arXiv preprint arXiv:2103.04564, 2021. [68] Gemini Robotics Team, Saminda Abeyruwan, Joshua Ainslie, Jean-Bapti","claim_type":"background","confidence":0.85,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Gemini Robotics: Bringing AI into the Physical World because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (29 contexts).","role_counts":[{"n":29,"context_role":"background"},{"n":4,"context_role":"dataset"},{"n":1,"context_role":"baseline"}]},"error":null,"updated_at":"2026-07-03T09:23:51.444635+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"dc9b5841-2076-4481-8842-2797bf5a4591","orcid":null,"display_name":"Gemini Robotics Team"},{"id":"e67b84a8-a7b8-48eb-a1d8-e036f6d17c9a","orcid":null,"display_name":"Saminda Abeyruwan"},{"id":"def23d27-3f7c-47c9-b553-45af77bcbb6a","orcid":null,"display_name":"Joshua Ainslie"},{"id":"44b3ddc4-9896-4039-9349-0e6fe7adb78c","orcid":null,"display_name":"Jean-Baptiste Alayrac"},{"id":"6a29424a-6f48-4e79-b3bb-8f1785fa9123","orcid":null,"display_name":"Montserrat Gonzalez Arenas"},{"id":"a1886269-dd43-4d9c-8205-83b43cc067eb","orcid":null,"display_name":"Travis Armstrong"}]},"error":null,"updated_at":"2026-07-03T09:23:52.004578+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T17:49:00.345838+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","work_id":"e2db69c7-ee8a-4cb7-a761-7b8de1dfcf97","shared_citers":18},{"title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","work_id":"f790abdc-a796-482f-a40d-f8ee035ecfc2","shared_citers":17},{"title":"OpenVLA: An Open-Source Vision-Language-Action Model","work_id":"3e7e65c5-5aed-4fe9-8414-2092bcb31cc7","shared_citers":16},{"title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","work_id":"d1ad7304-d09a-49bc-809e-846439f6aff9","shared_citers":15},{"title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","work_id":"04f46bb3-4346-47e8-bf09-c75d91f96e87","shared_citers":10},{"title":"GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation","work_id":"843ab5eb-2815-4db8-b3bc-890b23fa5ffa","shared_citers":9},{"title":"RT-1: Robotics Transformer for Real-World Control at Scale","work_id":"e11bda85-8531-46bc-a07f-d0ade3643ab1","shared_citers":9},{"title":"RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation","work_id":"12319725-bc7d-4c32-a229-ad270a7460bc","shared_citers":8},{"title":"SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics","work_id":"0c5e9314-5fa7-4613-ad12-605a71d561d2","shared_citers":8},{"title":"A Survey on Vision-Language-Action Models for Embodied AI","work_id":"9492fb3d-d667-4892-81bb-b2878f12ff0c","shared_citers":7},{"title":"CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation","work_id":"4b158d3e-3dff-4412-85cd-baa879465a5e","shared_citers":7},{"title":"Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning","work_id":"3d63039f-41b0-4a31-af31-6fc10f5c1b1b","shared_citers":7},{"title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","work_id":"83a8f966-6cfa-4f21-81f3-87440aae238f","shared_citers":7},{"title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","work_id":"008df105-2fdd-45d8-857a-8e35868aecb6","shared_citers":7},{"title":"LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models","work_id":"e35c8c6d-977d-4af1-963a-766ba98703ce","shared_citers":7},{"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","shared_citers":7},{"title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","work_id":"8abcfe4f-e0fb-44b7-9123-448fac95f90a","shared_citers":7},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":7},{"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","shared_citers":7},{"title":"RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation","work_id":"9b985126-4a2f-4bdf-b014-2a7524ec634e","shared_citers":7},{"title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","work_id":"ff438a8a-8003-4fae-9131-acd418b3597b","shared_citers":7},{"title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","work_id":"e05d654d-db73-48f6-9318-381b6798bac9","shared_citers":7},{"title":"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations","work_id":"62dbe235-8473-4190-8686-17e7437de50f","shared_citers":7},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":6}],"time_series":[{"n":3,"year":2025},{"n":36,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T17:48:36.488662+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"items":[{"title":"Qwen3 Technical Report","outcome":"unchanged","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"counts":{"fixed":0,"merged":0,"unchanged":1,"quarantined":0,"needs_external_resolution":0},"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-14T17:48:57.205552+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"Gemini Robotics: Bringing AI into the Physical World","claims":[{"claim_text":"Recent advancements in large multimodal models have led to the emergence of remarkable generalist capabilities in digital domains, yet their translation to physical agents such as robots remains a significant challenge. This report introduces a new family of AI models purposefully designed for robotics and built upon the foundation of Gemini 2.0. We present Gemini Robotics, an advanced Vision-Language-Action (VLA) generalist model capable of directly controlling robots. Gemini Robotics executes smooth and reactive movements to tackle a wide range of complex manipulation tasks while also being ","claim_type":"abstract","evidence_strength":"source_metadata"},{"claim_text":"Gemini: a family of highly capable multimodal models.arXiv preprint arXiv:2312.11805, 2023. [122] Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.arXiv preprint arXiv:2403.05530, 2024. [123] Gemini Robotics Team, Saminda Abeyruwan, Joshua Ainslie, Jean-Baptiste Alayrac, Montser- rat Gonzalez Arenas, Travis Armstrong,","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"extend the scaling laws [19, 20] observed in vision and language domains to the embodied setting, collecting large-scale embodied datasets and training generalist agents end-to-end on top of vision-language foundation models [21, 22, 23]. These diverse approaches have led to a rapid proliferation of VLA models in robotic manipulation [24, 25], navigation [26, 27], and autonomous driving [28, 29, 30], demonstrating promising capabilities in multitask learning [31], long-horizon task completion [2","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"9 64.3/73.1◦ Pointing & Counting CountBench [49] 91.0 91.0 91.097.391.8 96.3 FSC-147 [2]↓ 22.0 28.0 24.512.117.9 13.6 Point-Bench [14] 33.8 41.8 ∗ 62.7∗ 85.5∗ 74.9 76.5 2D & 3D Spatial Understanding BLINK [23] 63.4 69.6 70.677.172.1 74.3 MMSIBench (circular) [83] 17.2 22.3 17.6 25.4 11.7 25.8 RefSpatialBench [94] 21.7 28.2 ∗ 33.6∗ 65.5∗ 58.8 56.3 ERQA [63] 49.8 60.0 ∗ 56.0∗ 70.5∗ 47.0 58.8 DA-2K [82] 68.2 78.6 76.5 82.1 85.3 90.7 CV-Bench [65] 79.3 84.6 85.992.084.9 88.0 Document & Chart Underst","claim_type":"dataset","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"• OCR, Chart & Document: OCRBench [ 31], ChartQAPro [ 35], ChartMuseum [ 45], MMLongBench-Doc [34]; •Visual Grounding: RefCOCO-avg (val) [25], TreeBench [54], Ref-L4 [6]; •GUI Agents: OSWorld [62], Android World [38], WebV oyager Some [18], Webquest-QA [56]; •Coding: Design2Code [43], Flame-React-Eval [1]; • Spatial Reco & Reasoning: OminiSpatial [24], CV-Bench [51], ERQA [49], All-Angles Bench [65]; • Video Understanding: VideoMME [ 10], MMVU [ 71], VideoMMMU [ 22], LVBench [ 58], MotionBench [","claim_type":"dataset","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"5-VL performance on public video benchmarks compared to previous models. For all benchmarks, higher numbers are better. The evaluation frame rates are 2 FPS for MotionBench, MVBench, TOMATO, and TVBench, 3 FPS for Dream-1K, and 1 FPS for all other datasets. Capability Benchmark Seed OpenAI Claude UI-TARS Kimi Qwen 2.5 1.5-VL CUA [98] 3.7 Sonnet [6] 1.5 [116] VL-A3B [130] VL 72B [7] GUI Grounding ScreenSpot-V2 [149] 95.2 87.9 87 .6 94 .2 92.8 - ScreenSpot-Pro [72] 60.9 23.4 27 .7 61.6 34.5 43 .6 ","claim_type":"baseline","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"[66] DJ Strouse, Kevin McKee, Matt Botvinick, Edward Hughes, and Richard Everett. Collaborat- ing with humans without human data. Advances in Neural Information Processing Systems, 34:14502-14515, 2021. [67] Zhenggang Tang, Chao Yu, Boyuan Chen, Huazhe Xu, Xiaolong Wang, Fei Fang, Simon Du, Yu Wang, and Yi Wu. Discovering diverse multi-agent strategic behavior via reward randomization. arXiv preprint arXiv:2103.04564, 2021. [68] Gemini Robotics Team, Saminda Abeyruwan, Joshua Ainslie, Jean-Bapti","claim_type":"background","confidence":0.85,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Gemini Robotics: Bringing AI into the Physical World because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (29 contexts).","role_counts":[{"n":29,"context_role":"background"},{"n":4,"context_role":"dataset"},{"n":1,"context_role":"baseline"}]},"error":null,"updated_at":"2026-07-03T09:23:52.006932+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Gemini Robotics: Bringing AI into the Physical World","claims":[{"claim_text":"Recent advancements in large multimodal models have led to the emergence of remarkable generalist capabilities in digital domains, yet their translation to physical agents such as robots remains a significant challenge. This report introduces a new family of AI models purposefully designed for robotics and built upon the foundation of Gemini 2.0. We present Gemini Robotics, an advanced Vision-Language-Action (VLA) generalist model capable of directly controlling robots. Gemini Robotics executes smooth and reactive movements to tackle a wide range of complex manipulation tasks while also being ","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Gemini Robotics: Bringing AI into the Physical World because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T17:49:00.350432+00:00"}},"summary":{"title":"Gemini Robotics: Bringing AI into the Physical World","claims":[{"claim_text":"Recent advancements in large multimodal models have led to the emergence of remarkable generalist capabilities in digital domains, yet their translation to physical agents such as robots remains a significant challenge. This report introduces a new family of AI models purposefully designed for robotics and built upon the foundation of Gemini 2.0. We present Gemini Robotics, an advanced Vision-Language-Action (VLA) generalist model capable of directly controlling robots. Gemini Robotics executes smooth and reactive movements to tackle a wide range of complex manipulation tasks while also being ","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Gemini Robotics: Bringing AI into the Physical World because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","work_id":"e2db69c7-ee8a-4cb7-a761-7b8de1dfcf97","shared_citers":18},{"title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","work_id":"f790abdc-a796-482f-a40d-f8ee035ecfc2","shared_citers":17},{"title":"OpenVLA: An Open-Source Vision-Language-Action Model","work_id":"3e7e65c5-5aed-4fe9-8414-2092bcb31cc7","shared_citers":16},{"title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","work_id":"d1ad7304-d09a-49bc-809e-846439f6aff9","shared_citers":15},{"title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","work_id":"04f46bb3-4346-47e8-bf09-c75d91f96e87","shared_citers":10},{"title":"GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation","work_id":"843ab5eb-2815-4db8-b3bc-890b23fa5ffa","shared_citers":9},{"title":"RT-1: Robotics Transformer for Real-World Control at Scale","work_id":"e11bda85-8531-46bc-a07f-d0ade3643ab1","shared_citers":9},{"title":"RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation","work_id":"12319725-bc7d-4c32-a229-ad270a7460bc","shared_citers":8},{"title":"SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics","work_id":"0c5e9314-5fa7-4613-ad12-605a71d561d2","shared_citers":8},{"title":"A Survey on Vision-Language-Action Models for Embodied AI","work_id":"9492fb3d-d667-4892-81bb-b2878f12ff0c","shared_citers":7},{"title":"CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation","work_id":"4b158d3e-3dff-4412-85cd-baa879465a5e","shared_citers":7},{"title":"Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning","work_id":"3d63039f-41b0-4a31-af31-6fc10f5c1b1b","shared_citers":7},{"title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","work_id":"83a8f966-6cfa-4f21-81f3-87440aae238f","shared_citers":7},{"title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","work_id":"008df105-2fdd-45d8-857a-8e35868aecb6","shared_citers":7},{"title":"LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models","work_id":"e35c8c6d-977d-4af1-963a-766ba98703ce","shared_citers":7},{"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","shared_citers":7},{"title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","work_id":"8abcfe4f-e0fb-44b7-9123-448fac95f90a","shared_citers":7},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":7},{"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","shared_citers":7},{"title":"RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation","work_id":"9b985126-4a2f-4bdf-b014-2a7524ec634e","shared_citers":7},{"title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","work_id":"ff438a8a-8003-4fae-9131-acd418b3597b","shared_citers":7},{"title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","work_id":"e05d654d-db73-48f6-9318-381b6798bac9","shared_citers":7},{"title":"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations","work_id":"62dbe235-8473-4190-8686-17e7437de50f","shared_citers":7},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":6}],"time_series":[{"n":3,"year":2025},{"n":36,"year":2026}],"dependency_candidates":[]},"authors":[{"id":"dc9b5841-2076-4481-8842-2797bf5a4591","orcid":null,"display_name":"Gemini Robotics Team","source":"manual","import_confidence":0.72},{"id":"44b3ddc4-9896-4039-9349-0e6fe7adb78c","orcid":null,"display_name":"Jean-Baptiste Alayrac","source":"manual","import_confidence":0.72},{"id":"def23d27-3f7c-47c9-b553-45af77bcbb6a","orcid":null,"display_name":"Joshua Ainslie","source":"manual","import_confidence":0.72},{"id":"6a29424a-6f48-4e79-b3bb-8f1785fa9123","orcid":null,"display_name":"Montserrat Gonzalez Arenas","source":"manual","import_confidence":0.72},{"id":"e67b84a8-a7b8-48eb-a1d8-e036f6d17c9a","orcid":null,"display_name":"Saminda Abeyruwan","source":"manual","import_confidence":0.72},{"id":"a1886269-dd43-4d9c-8205-83b43cc067eb","orcid":null,"display_name":"Travis Armstrong","source":"manual","import_confidence":0.72}]}}