mlsanityData to 7 Oct 2026

LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning

arXiv 2306.03310 ↗First posted 5 Jun 2023cs.AIcited by 1,338

Not on the map. Why?

Cited by 810 in Vision-language-action models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Lifelong learning offers a promising paradigm of building a generalist agent that learns and adapts over its lifespan. Unlike traditional lifelong learning problems in image and text domains, which primarily involve the transfer of declarative knowledge of entities and concepts, lifelong learning in decision-making (LLDM) also necessitates the transfer of procedural knowledge, such as actions and behaviors. To advance research in LLDM, we introduce LIBERO, a novel benchmark of lifelong learning for robot manipulation. Specifically, LIBERO highlights five key research topics in LLDM: 1) how to efficiently transfer declarative knowledge, procedural knowledge, or the mixture of both; 2) how to design effective policy architectures and 3) effective algorithms for LLDM; 4) the robustness of a lifelong learner with respect to task ordering; and 5) the effect of model pretraining for LLDM. We develop an extendible procedural generation pipeline that can in principle generate infinitely many tasks. For benchmarking purpose, we create four task suites (130 tasks in total) that we use to investigate the above-mentioned research topics. To support sample-efficient learning, we provide high-quality human-teleoperated demonstration data for all tasks. Our extensive experiments present several insightful or even unexpected discoveries: sequential finetuning outperforms existing lifelong learning methods in forward transfer, no single visual encoder architecture excels at all types of knowledge transfer, and naive supervised pretraining can hinder agents' performance in the subsequent LLDM. Check the website at https://libero-project.github.io for the code and the datasets.

Key facts. Cited by 1,338 papers in the map (data through 7 Oct 2026). Builds on 61 of its 90 references that are in the map. First posted on arXiv 5 Jun 2023.

Builds on

61 of 90 references.

References · 61

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  5. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  6. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  7. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  8. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  9. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  10. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  11. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  12. 2016Progressive Neural Networkscited by 1,332
38 more
  1. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  2. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,224
  3. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,168
  4. 2018Efficient Lifelong Learning with A-GEMcited by 1,044
  5. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 895
  6. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 882
  7. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 773
  8. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 734
  9. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 699
  10. 2017Lifelong Learning with Dynamically Expandable Networkscited by 689
  11. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 669
  12. 2018Progress & Compress: A scalable framework for continual learningcited by 516
  13. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 484
  14. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 478
  15. 2015Deep Recurrent Q-Learning for Partially Observable MDPscited by 457
  16. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 350
  17. 2023ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skillscited by 313
  18. 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 287
  19. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 242
  20. 2023MimicPlay: Long-Horizon Imitation Learning by Watching Human Playcited by 214
  21. 2019Compacting, Picking and Growing for Unforgetting Continual Learningcited by 207
  22. 2021ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrationscited by 193
  23. 2016ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learningcited by 178
  24. 2021Open-Ended Learning Leads to Generally Capable Agentscited by 177
  25. 2021BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environmentscited by 161
  26. 2020Continual Lifelong Learning in Natural Language Processing: A Surveycited by 152
  27. 2017Visualizing and Understanding Atari Agentscited by 141
  28. 2022VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priorscited by 135
  29. 2022Forward Compatible Few-Shot Class-Incremental Learningcited by 125
  30. 2022Continual Learning and Private Unlearningcited by 124
  31. 2018Don't forget, there is more than forgetting: new metrics for Continual Learningcited by 113
  32. 2022Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidationcited by 113
  33. 2021Continual World: A Robotic Benchmark For Continual Reinforcement Learningcited by 112
  34. 2020CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learningcited by 109
  35. 2021MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Researchcited by 96
  36. 2019Superposition of many models into onecited by 64
  37. 2021Firefly Neural Architecture Descent: a General Approach for Growing Neural Networkscited by 48
  38. 2022Architecture Matters in Continual Learningcited by 46

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 47; 2025: 342; 2026: 942.

1,338 papers.

Sort:

By area:

  1. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  2. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 844
  3. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 507
  4. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 502
  5. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 477
  6. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 440
  7. 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 391
  8. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 386
  9. 2025WorldVLA: Towards Autoregressive Action World Modelcited by 351
  10. 2026Fast-WAM: Do World Action Models Need Test-time Future Imagination?cited by 311
  11. 2026Causal World Modeling for Robot Controlcited by 289
  12. 2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Modelcited by 285
38 more
  1. 2025LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Modelscited by 278
  2. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 274
  3. 2026Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planningcited by 274
  4. 2025Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasetscited by 218
  5. 2023Any-point Trajectory Modeling for Policy Learningcited by 207
  6. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 203
  7. 2025Unified Video Action Modelcited by 195
  8. 2025MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulationcited by 183
  9. 2024VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Taskscited by 171
  10. 2025VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learningcited by 166
  11. 2025LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorizationcited by 166
  12. 2024Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulationcited by 159
  13. 2025Cosmos-Reason1: From Physical Common Sense To Embodied Reasoningcited by 159
  14. 2025ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planningcited by 152
  15. 2025Steering Your Diffusion Policy with Latent Space Reinforcement Learningcited by 149
  16. 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Bettercited by 142
  17. 2025SimpleVLA-RL: Scaling VLA Training via Reinforcement Learningcited by 141
  18. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Modelcited by 140
  19. 2025mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAscited by 133
  20. 2023Large Language Models for Robotics: A Surveycited by 132
  21. 2024Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goalscited by 131
  22. 2025Interactive Post-Training for Vision-Language-Action Modelscited by 129
  23. 2025Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulationcited by 129
  24. 2024THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulationcited by 128
  25. 2025Unified Vision-Language-Action Modelcited by 128
  26. 2025Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Modelcited by 125
  27. 2025GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Datacited by 120
  28. 2025NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Taskscited by 119
  29. 2025EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videoscited by 116
  30. 2024BootsTAP: Bootstrapped Training for Tracking-Any-Pointcited by 115
  31. 2025AdaWorld: Learning Adaptable World Models with Latent Actionscited by 108
  32. 2024GRAPE: Generalizing Robot Policy via Preference Alignmentcited by 106
  33. 2026VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Modelcited by 104
  34. 2026StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developingcited by 103
  35. 2026A Pragmatic VLA Foundation Modelcited by 97
  36. 2026ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learningcited by 94
  37. 2024IRASim: A Fine-Grained World Model for Robot Manipulationcited by 93
  38. 2025Controllable Video Generation: A Surveycited by 93

50 most cited of 1,338 All 1,338 (JSON)