{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/robot-manipulation/papers/3","list_of":"/task/robot-manipulation","task":"Robot Manipulation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":3,"pages_in_order":5,"rows_per_page":100,"rows":[201,300],"of":430,"counts":{"archive_papers_tagged":430,"with_a_code_link":154,"where_syntology_ran_a_sample":62,"not_listed_spam_title":0,"listed":430,"listed_where_code_ran":62,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":53,"every_run_a_failure_of_syntologys_instrument":9,"listed_with_a_run_with_no_instrument_failure":53,"listed_every_run_a_failure_of_syntologys_instrument":9,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/robot-manipulation","prev":"/task/robot-manipulation/papers/2","next":"/task/robot-manipulation/papers/4","papers":[{"url":null,"slug":"s-2-diffusion-generalizing-from-instance","title":"S$^2$-Diffusion: Generalizing from Instance-level to Category-level Skills in Robot Manipulation","date":"2025-02-13","arxiv_id":"2502.09389","repositories_listed":0,"syntology":null},{"url":null,"slug":"combo-grasp-learning-constraint-based","title":"COMBO-Grasp: Learning Constraint-Based Manipulation for Bimanual Occluded Grasping","date":"2025-02-12","arxiv_id":"2502.08054","repositories_listed":0,"syntology":null},{"url":null,"slug":"select-before-act-spatially-decoupled-action","title":"Select before Act: Spatially Decoupled Action Repetition for Continuous Control","date":"2025-02-10","arxiv_id":"2502.06919","repositories_listed":0,"syntology":null},{"url":null,"slug":"hamster-hierarchical-action-models-for-open","title":"HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation","date":"2025-02-08","arxiv_id":"2502.05485","repositories_listed":0,"syntology":null},{"url":null,"slug":"anyplace-learning-generalized-object","title":"AnyPlace: Learning Generalized Object Placement for Robot Manipulation","date":"2025-02-06","arxiv_id":"2502.04531","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-latent-representations-in-behavior","title":"Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation","date":"2025-02-05","arxiv_id":"2502.02853","repositories_listed":0,"syntology":null},{"url":"/paper/up-vla-a-unified-understanding-and-prediction","slug":"up-vla-a-unified-understanding-and-prediction","title":"UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent","date":"2025-01-31","arxiv_id":"2501.18867","repositories_listed":0,"syntology":null},{"url":null,"slug":"strong-and-controllable-3d-motion-generation","title":"Strong and Controllable 3D Motion Generation","date":"2025-01-30","arxiv_id":"2501.18726","repositories_listed":0,"syntology":null},{"url":"/paper/spatialvla-exploring-spatial-representations","slug":"spatialvla-exploring-spatial-representations","title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","date":"2025-01-27","arxiv_id":"2501.15830","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-sight-finetuning-generalist-robot","title":"Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Grounding","date":"2025-01-08","arxiv_id":"2501.04693","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-transfer-human-hand-skills-for","title":"Learning to Transfer Human Hand Skills for Robot Manipulations","date":"2025-01-07","arxiv_id":"2501.04169","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-mvp-3d-multiview-pretraining-for","title":"3D-MVP: 3D Multiview Pretraining for Manipulation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"embodied-videoagent-persistent-memory-from","title":"Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding","date":"2024-12-31","arxiv_id":"2501.00358","repositories_listed":0,"syntology":null},{"url":null,"slug":"robomind-benchmark-on-multi-embodiment","title":"RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation","date":"2024-12-18","arxiv_id":"2412.13877","repositories_listed":0,"syntology":null},{"url":null,"slug":"manipgpt-is-affordance-segmentation-by-large","title":"ManipGPT: Is Affordance Segmentation by Large Vision Models Enough for Articulated Object Manipulation?","date":"2024-12-13","arxiv_id":"2412.10050","repositories_listed":0,"syntology":null},{"url":"/paper/tracevla-visual-trace-prompting-enhances","slug":"tracevla-visual-trace-prompting-enhances","title":"TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies","date":"2024-12-13","arxiv_id":"2412.10345","repositories_listed":0,"syntology":null},{"url":null,"slug":"grasp-diffusion-network-learning-grasp","title":"Grasp Diffusion Network: Learning Grasp Generators from Partial Point Clouds with Diffusion Models in SO(3)xR3","date":"2024-12-11","arxiv_id":"2412.08398","repositories_listed":0,"syntology":null},{"url":null,"slug":"p3-po-prescriptive-point-priors-for-visuo","title":"P3-PO: Prescriptive Point Priors for Visuo-Spatial Generalization of Robot Policies","date":"2024-12-09","arxiv_id":"2412.06784","repositories_listed":0,"syntology":null},{"url":null,"slug":"variable-speed-teaching-playback-as-real","title":"Variable-Speed Teaching-Playback as Real-World Data Augmentation for Imitation Learning","date":"2024-12-04","arxiv_id":"2412.03252","repositories_listed":0,"syntology":null},{"url":null,"slug":"robofail-analyzing-failures-in-robot-learning","title":"From Mystery to Mastery: Failure Diagnosis for Improving Manipulation Policies","date":"2024-12-03","arxiv_id":"2412.02818","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantization-aware-imitation-learning-for","title":"Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control","date":"2024-12-02","arxiv_id":"2412.01034","repositories_listed":0,"syntology":null},{"url":null,"slug":"prediction-with-action-visual-policy-learning","title":"Prediction with Action: Visual Policy Learning via Joint Denoising Process","date":"2024-11-27","arxiv_id":"2411.18179","repositories_listed":0,"syntology":null},{"url":null,"slug":"robospatial-teaching-spatial-understanding-to","title":"RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics","date":"2024-11-25","arxiv_id":"2411.16537","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-the-intermediate-features-in","title":"Rethinking the Intermediate Features in Adversarial Attacks: Misleading Robotic Models via Adversarial Distillation","date":"2024-11-21","arxiv_id":"2411.15222","repositories_listed":0,"syntology":null},{"url":"/paper/vidman-exploiting-implicit-dynamics-from","slug":"vidman-exploiting-implicit-dynamics-from","title":"VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot Manipulation","date":"2024-11-14","arxiv_id":"2411.09153","repositories_listed":0,"syntology":null},{"url":null,"slug":"et-seed-efficient-trajectory-level-se-3","title":"ET-SEED: Efficient Trajectory-Level SE(3) Equivariant Diffusion Policy","date":"2024-11-06","arxiv_id":"2411.03990","repositories_listed":0,"syntology":null},{"url":null,"slug":"rt-affordance-affordances-are-versatile","title":"RT-Affordance: Affordances are Versatile Intermediate Representations for Robot Manipulation","date":"2024-11-05","arxiv_id":"2411.02704","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-rigid-relative-placement-through-3d-dense","title":"Non-rigid Relative Placement through 3D Dense Diffusion","date":"2024-10-25","arxiv_id":"2410.19247","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-look-seeking-information-for","title":"Learning to Look: Seeking Information for Decision Making via Policy Factorization","date":"2024-10-24","arxiv_id":"2410.18964","repositories_listed":0,"syntology":null},{"url":null,"slug":"skillmimicgen-automated-demonstration","title":"SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment","date":"2024-10-24","arxiv_id":"2410.18907","repositories_listed":0,"syntology":null},{"url":null,"slug":"spire-synergistic-planning-imitation-and","title":"SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulation","date":"2024-10-23","arxiv_id":"2410.18065","repositories_listed":0,"syntology":null},{"url":null,"slug":"worldsimbench-towards-video-generation-models","title":"WorldSimBench: Towards Video Generation Models as World Simulators","date":"2024-10-23","arxiv_id":"2410.18072","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-weight-diffusion-generating-policies","title":"Latent Weight Diffusion: Generating reactive policies instead of trajectories","date":"2024-10-17","arxiv_id":"2410.14040","repositories_listed":0,"syntology":null},{"url":"/paper/towards-synergistic-generalized-and-efficient","slug":"towards-synergistic-generalized-and-efficient","title":"Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation","date":"2024-10-10","arxiv_id":"2410.08001","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-planning-and-diffusion-for-mobility","title":"Combining Planning and Diffusion for Mobility with Unknown Dynamics","date":"2024-10-09","arxiv_id":"2410.06911","repositories_listed":0,"syntology":null},{"url":null,"slug":"gr-2-a-generative-video-language-action-model","title":"GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation","date":"2024-10-08","arxiv_id":"2410.06158","repositories_listed":0,"syntology":null},{"url":null,"slug":"absolute-state-wise-constrained-policy","title":"Absolute State-wise Constrained Policy Optimization: High-Probability State-wise Constraints Satisfaction","date":"2024-10-02","arxiv_id":"2410.01212","repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-tuning-strategies-for-generalist","title":"Effective Tuning Strategies for Generalist Robot Manipulation Policies","date":"2024-10-02","arxiv_id":"2410.01220","repositories_listed":0,"syntology":null},{"url":null,"slug":"gen2act-human-video-generation-in-novel","title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","date":"2024-09-24","arxiv_id":"2409.16283","repositories_listed":0,"syntology":null},{"url":null,"slug":"robot-manipulation-in-salient-vision-through","title":"Robot Manipulation in Salient Vision through Referring Image Segmentation and Geometric Constraints","date":"2024-09-17","arxiv_id":"2409.11518","repositories_listed":0,"syntology":null},{"url":null,"slug":"hand-object-interaction-pretraining-from","title":"Hand-Object Interaction Pretraining from Videos","date":"2024-09-12","arxiv_id":"2409.08273","repositories_listed":0,"syntology":null},{"url":null,"slug":"madiff-motion-aware-mamba-diffusion-models","title":"MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videos","date":"2024-09-04","arxiv_id":"2409.02638","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantically-controllable-augmentations-for","title":"Semantically Controllable Augmentations for Generalizable Robot Learning","date":"2024-09-02","arxiv_id":"2409.00951","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-adaptation-via-language-optimization","title":"Policy Adaptation via Language Optimization: Decomposing Tasks for Few-Shot Imitation","date":"2024-08-29","arxiv_id":"2408.16228","repositories_listed":0,"syntology":null},{"url":null,"slug":"physpart-physically-plausible-part-completion","title":"PhysPart: Physically Plausible Part Completion for Interactable Objects","date":"2024-08-25","arxiv_id":"2408.13724","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02882","title":"Compromising Embodied Agents with Contextual Backdoor Attacks","date":"2024-08-06","arxiv_id":"2408.02882","repositories_listed":0,"syntology":null},{"url":null,"slug":"hacman-spatially-grounded-motion-primitives","title":"HACMan++: Spatially-Grounded Motion Primitives for Manipulation","date":"2024-07-11","arxiv_id":"2407.08585","repositories_listed":0,"syntology":null},{"url":null,"slug":"category-level-object-detection-pose","title":"Category-level Object Detection, Pose Estimation and Reconstruction from Stereo Images","date":"2024-07-09","arxiv_id":"2407.06984","repositories_listed":0,"syntology":null},{"url":null,"slug":"equibot-sim-3-equivariant-diffusion-policy","title":"EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learning","date":"2024-07-01","arxiv_id":"2407.01479","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-agent-joint-learning-for-efficient","title":"Human-Agent Joint Learning for Efficient Robot Manipulation Skill Acquisition","date":"2024-06-29","arxiv_id":"2407.00299","repositories_listed":0,"syntology":null},{"url":null,"slug":"manipulate-anything-automating-real-world","title":"Manipulate-Anything: Automating Real-World Robots using Vision-Language Models","date":"2024-06-27","arxiv_id":"2406.18915","repositories_listed":0,"syntology":null},{"url":null,"slug":"maniwav-learning-robot-manipulation-from-in","title":"ManiWAV: Learning Robot Manipulation from In-the-Wild Audio-Visual Data","date":"2024-06-27","arxiv_id":"2406.19464","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-feature-distillation-with-object-centric","title":"3D Feature Distillation with Object-Centric Priors","date":"2024-06-26","arxiv_id":"2406.18742","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-mvp-3d-multiview-pretraining-for-robotic","title":"3D-MVP: 3D Multiview Pretraining for Robotic Manipulation","date":"2024-06-26","arxiv_id":"2406.18158","repositories_listed":0,"syntology":null},{"url":null,"slug":"extract-efficient-policy-learning-by","title":"EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Data","date":"2024-06-25","arxiv_id":"2406.17768","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-the-llm-based-robot-manipulation","title":"Enhancing the LLM-Based Robot Manipulation Through Human-Robot Collaboration","date":"2024-06-20","arxiv_id":"2406.14097","repositories_listed":0,"syntology":null},{"url":null,"slug":"cycle-correspondence-loss-learning-dense-view","title":"Cycle-Correspondence Loss: Learning Dense View-Invariant Visual Features from Unlabeled and Unordered RGB Images","date":"2024-06-18","arxiv_id":"2406.12441","repositories_listed":0,"syntology":null},{"url":"/paper/robomamba-multimodal-state-space-model-for","slug":"robomamba-multimodal-state-space-model-for","title":"RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation","date":"2024-06-06","arxiv_id":"2406.04339","repositories_listed":0,"syntology":null},{"url":"/paper/sam-e-leveraging-visual-foundation-model-with","slug":"sam-e-leveraging-visual-foundation-model-with","title":"SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation","date":"2024-05-30","arxiv_id":"2405.19586","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-based-manipulation-from-single-human","title":"Vision-based Manipulation from Single Human Video with Open-World Object Graphs","date":"2024-05-30","arxiv_id":"2405.20321","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-recover-from-plan-execution","title":"Learning to Recover from Plan Execution Errors during Robot Manipulation: A Neuro-symbolic Approach","date":"2024-05-29","arxiv_id":"2405.18948","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-corrected-multimodal-large-language","title":"Self-Corrected Multimodal Large Language Model for End-to-End Robot Manipulation","date":"2024-05-27","arxiv_id":"2405.17418","repositories_listed":0,"syntology":null},{"url":"/paper/octo-an-open-source-generalist-robot-policy","slug":"octo-an-open-source-generalist-robot-policy","title":"Octo: An Open-Source Generalist Robot Policy","date":"2024-05-20","arxiv_id":"2405.12213","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffgen-robot-demonstration-generation-via","title":"DiffGen: Robot Demonstration Generation via Differentiable Physics Simulation, Differentiable Rendering, and Vision-Language Model","date":"2024-05-12","arxiv_id":"2405.07309","repositories_listed":0,"syntology":null},{"url":"/paper/from-llms-to-actions-latent-codes-as-bridges","slug":"from-llms-to-actions-latent-codes-as-bridges","title":"From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control","date":"2024-05-08","arxiv_id":"2405.04798","repositories_listed":0,"syntology":null},{"url":null,"slug":"track2act-predicting-point-tracks-from","title":"Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation","date":"2024-05-02","arxiv_id":"2405.01527","repositories_listed":0,"syntology":null},{"url":null,"slug":"closed-loop-interactive-embodied-reasoning","title":"Closed Loop Interactive Embodied Reasoning for Robot Manipulation","date":"2024-04-23","arxiv_id":"2404.15194","repositories_listed":0,"syntology":null},{"url":null,"slug":"sketch-plan-generalize-continual-few-shot","title":"Sketch-Plan-Generalize: Learning and Planning with Neuro-Symbolic Programmatic Representations for Inductive Spatial Concepts","date":"2024-04-11","arxiv_id":"2404.07774","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-neuromorphic-approach-to-obstacle-avoidance","title":"A Neuromorphic Approach to Obstacle Avoidance in Robot Manipulation","date":"2024-04-08","arxiv_id":"2404.05858","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-exploration-in-bayesian-model-based","title":"Active Exploration in Bayesian Model-based Reinforcement Learning for Robot Manipulation","date":"2024-04-02","arxiv_id":"2404.01867","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-search-based-planning-for-multi","title":"Accelerating Search-Based Planning for Multi-Robot Manipulation by Leveraging Online-Generated Experiences","date":"2024-03-29","arxiv_id":"2404.00143","repositories_listed":0,"syntology":null},{"url":null,"slug":"riemann-near-real-time-se-3-equivariant-robot","title":"RiEMann: Near Real-Time SE(3)-Equivariant Robot Manipulation without Point Cloud Segmentation","date":"2024-03-28","arxiv_id":"2403.19460","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-language-plans-in-demonstrations","title":"Grounding Language Plans in Demonstrations Through Counterfactual Perturbations","date":"2024-03-25","arxiv_id":"2403.17124","repositories_listed":0,"syntology":null},{"url":null,"slug":"physics-based-causal-reasoning-for-safe","title":"COBRA-PPM: A Causal Bayesian Reasoning Architecture Using Probabilistic Programming for Robot Manipulation Under Uncertainty","date":"2024-03-21","arxiv_id":"2403.14488","repositories_listed":0,"syntology":null},{"url":null,"slug":"visarl-visual-reinforcement-learning-guided","title":"ViSaRL: Visual Reinforcement Learning Guided by Human Saliency","date":"2024-03-16","arxiv_id":"2403.10940","repositories_listed":0,"syntology":null},{"url":null,"slug":"naturalvlm-leveraging-fine-grained-natural","title":"NaturalVLM: Leveraging Fine-grained Natural Language for Affordance-Guided Visual Manipulation","date":"2024-03-13","arxiv_id":"2403.08355","repositories_listed":0,"syntology":null},{"url":null,"slug":"never-ending-embodied-robot-learning","title":"Never-Ending Behavior-Cloning Agent for Robotic Manipulation","date":"2024-03-01","arxiv_id":"2403.00336","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-robotic-manipulation-with-ai","title":"Enhancing Robotic Manipulation with AI Feedback from Multimodal Large Language Models","date":"2024-02-22","arxiv_id":"2402.14245","repositories_listed":0,"syntology":null},{"url":null,"slug":"roboscript-code-generation-for-free-form","title":"RoboScript: Code Generation for Free-Form Manipulation Tasks across Real and Simulation","date":"2024-02-22","arxiv_id":"2402.14623","repositories_listed":0,"syntology":null},{"url":null,"slug":"dinobot-robot-manipulation-via-retrieval-and","title":"DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Models","date":"2024-02-20","arxiv_id":"2402.13181","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-by-watching-a-review-of-video-based","title":"Learning by Watching: A Review of Video-based Learning Approaches for Robot Manipulation","date":"2024-02-11","arxiv_id":"2402.07127","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-efficient-generalizable-framework-for","title":"Efficient Training of Generalizable Visuomotor Policies via Control-Aware Augmentation","date":"2024-01-17","arxiv_id":"2401.09258","repositories_listed":0,"syntology":null},{"url":null,"slug":"swbt-similarity-weighted-behavior-transformer","title":"Learning from Imperfect Demonstrations with Self-Supervision for Robotic Manipulation","date":"2024-01-17","arxiv_id":"2401.08957","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-robot-data-for-dual-arm-fine","title":"Multi-task real-robot data with gaze attention for dual-arm fine manipulation","date":"2024-01-15","arxiv_id":"2401.07603","repositories_listed":0,"syntology":null},{"url":null,"slug":"robo-abc-affordance-generalization-beyond","title":"Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation","date":"2024-01-15","arxiv_id":"2401.07487","repositories_listed":0,"syntology":null},{"url":null,"slug":"moto-offline-pre-training-to-online-fine","title":"MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning","date":"2024-01-06","arxiv_id":"2401.03306","repositories_listed":0,"syntology":null},{"url":null,"slug":"generate-subgoal-images-before-act-unlocking","title":"Generate Subgoal Images before Act: Unlocking the Chain-of-Thought Reasoning in Diffusion Model for Robot Manipulation with Multimodal Prompts","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"manipllm-embodied-multimodal-large-language","title":"ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation","date":"2023-12-24","arxiv_id":"2312.16217","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-role-of-the-action-space-in-robot","title":"On the Role of the Action Space in Robot Manipulation Learning and Sim-to-Real Transfer","date":"2023-12-06","arxiv_id":"2312.03673","repositories_listed":0,"syntology":null},{"url":null,"slug":"contact-energy-based-hindsight-experience","title":"Contact Energy Based Hindsight Experience Prioritization","date":"2023-12-05","arxiv_id":"2312.02677","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-generalizable-zero-shot-manipulation","title":"Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Plans","date":"2023-12-01","arxiv_id":"2312.00775","repositories_listed":0,"syntology":null},{"url":null,"slug":"interact-transformer-models-for-human-intent","title":"InteRACT: Transformer Models for Human Intent Prediction Conditioned on Robot Actions","date":"2023-11-21","arxiv_id":"2311.12943","repositories_listed":0,"syntology":null},{"url":null,"slug":"gpt-4v-ision-for-robotics-multimodal-task","title":"GPT-4V(ision) for Robotics: Multimodal Task Planning from Human Demonstration","date":"2023-11-20","arxiv_id":"2311.12015","repositories_listed":0,"syntology":null},{"url":null,"slug":"lotus-continual-imitation-learning-for-robot","title":"LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery","date":"2023-11-03","arxiv_id":"2311.02058","repositories_listed":0,"syntology":null},{"url":null,"slug":"score-models-for-offline-goal-conditioned","title":"SMORE: Score Models for Offline Goal-Conditioned Reinforcement Learning","date":"2023-11-03","arxiv_id":"2311.02013","repositories_listed":0,"syntology":null},{"url":"/paper/vision-language-foundation-models-as","slug":"vision-language-foundation-models-as","title":"Vision-Language Foundation Models as Effective Robot Imitators","date":"2023-11-02","arxiv_id":"2311.01378","repositories_listed":0,"syntology":null},{"url":null,"slug":"6-dof-stability-field-via-diffusion-models","title":"6-DoF Stability Field via Diffusion Models","date":"2023-10-26","arxiv_id":"2310.17649","repositories_listed":0,"syntology":null},{"url":null,"slug":"robot-fine-tuning-made-easy-pre-training","title":"Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning","date":"2023-10-23","arxiv_id":"2310.15145","repositories_listed":0,"syntology":null},{"url":null,"slug":"manicast-collaborative-manipulation-with-cost","title":"ManiCast: Collaborative Manipulation with Cost-Aware Human Forecasting","date":"2023-10-20","arxiv_id":"2310.13258","repositories_listed":0,"syntology":null},{"url":null,"slug":"mastering-robot-manipulation-with-multimodal","title":"Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning","date":"2023-10-14","arxiv_id":"2310.09676","repositories_listed":0,"syntology":null}],"record_sha256":"a439e6a6f2b14e283cb7922a7671bcb0ec671974da385ec7da05cd5e62530673","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}