mlsanityData to 7 Oct 2026

Language-conditioned policies and VLAs

162 papers0 this weekLow confidence in this grouping: the papers may belong to more than one topic, or the group may changeLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About

Keywords: language, vla, failure, imitation, imitation learning

Key facts. Language-conditioned policies and VLAs: 162 papers on arXiv since 2018 (data through 7 Oct 2026). 8 of its 162 mapped papers (5%) cite “Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation” (2018, arXiv 1811.10092). 5 of its 162 mapped papers (3%) cite “Language-Conditioned Imitation Learning for Robot Manipulation Tasks” (2020, arXiv 2010.12083). 5 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

5 new papers, 17 Sep – 7 Oct; 0 this week.

  1. Earlier · 5
  2. Iterative Policy Refinement through Semantic Rollout Analysis also fits: Imitation learning methods
  3. Does Continual Imitation Learning Remain Grounded? A Language-Perturbed Benchmark for Robotic Task Retention
  4. Looking Back to Move Forward: Temporal Verification for Generative Robot Policies also fits: Robot manipulation imitation learning
  5. Multi-Granularity Language-Guided Imitation Learning via Instruction Decomposition also fits: Robot manipulation imitation learning
  6. Towards VLA-Dreamer: Refining VLA Behavior Using World Models

Foundations

Most cited by papers here

  1. Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation2018cited by 8 here
  2. Language-Conditioned Imitation Learning for Robot Manipulation Tasks2020cited by 5 here
  3. Offline RL for Natural Language Generation with Implicit Language Q Learning2022cited by 4 here
  4. Offline Reinforcement Learning for Visual Navigation2022cited by 4 here
  5. Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning2018cited by 3 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 8 here
  2. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 19 here
  3. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 17 here
  4. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 10 here
  5. 2021A Minimalist Approach to Offline Reinforcement Learningcited by 7 here
  6. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 14 here
  7. 2022Offline RL for Natural Language Generation with Implicit Language Q Learningcited by 4 here
17 more it builds on, not in this chain
  1. 2018Self-Imitation Learningcited by 3 here
  2. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learningcited by 3 here
  3. 2018An Algorithmic Perspective on Imitation Learningcited by 6 here
  4. 2018Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigationcited by 8 here
  5. 2018Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learningcited by 3 here
  6. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 7 here
  7. 2019Goal-conditioned Imitation Learningcited by 4 here
  8. 2019A Divergence Minimization Perspective on Imitation Learning Methodscited by 5 here
  9. 2019Imitation Learning via Off-Policy Distribution Matchingcited by 6 here
  10. 2020Strictly Batch Imitation Learning by Energy-based Distribution Matchingcited by 6 here
  11. 2020Language-Conditioned Imitation Learning for Robot Manipulation Taskscited by 5 here
  12. 2021IQ-Learn: Inverse soft-Q Learning for Imitationcited by 4 here
  13. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 4 here
  14. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 4 here
  15. 2022Offline Reinforcement Learning for Visual Navigationcited by 4 here
  16. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 7 here
  17. 2023RoboCLIP: One Demonstration is Enough to Learn Robot Policiescited by 6 here

The 24 most cited of 280.

Browse

30 of 162, ranked 6–35

  1. 6Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies20253
  2. 7ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning20253
  3. 8Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning20243
  4. 9Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progress20243
  5. 10Model-Based Runtime Monitoring with Interactive Imitation Learning20233
  6. 11What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Data20223
  7. 12Language Conditioned Imitation Learning over Unstructured Data20203
  8. 13Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog20193
  9. 14Supervised Fine-Tuning as Inverse Reinforcement Learning20242
  10. 15Imitating Language via Scalable Inverse Reinforcement Learning20242
All 30
  1. 16How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective20242
  2. 17Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning20242
  3. 18LISA: Learning Interpretable Skill Abstractions from Language20222
  4. 19CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning20222
  5. 20Text Generation by Learning from Demonstrations20202
  6. 21Human-centric Dialog Training via Offline Reinforcement Learning20202
  7. 22Guiding Policies with Language via Meta-Learning20182
  8. 23ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations20251
  9. 24Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization20251
  10. 25From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models20251
  11. 26CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning20251
  12. 27Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models20251
  13. 28Failure Prediction at Runtime for Generative Robot Policies20251
  14. 29InFeR: Informed Failure Resilience in Learned Visual Navigation Control20251
  15. 30Preference-Conditioned Language-Guided Abstraction20241
  16. 31Policy Improvement using Language Feedback Models20241
  17. 32Rethinking Mutual Information for Language Conditioned Skill Discovery on Imitation Learning20241
  18. 33RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning20241
  19. 34SEAL: SEmantic-Augmented Imitation Learning via Language Model20241
  20. 35Real-World Offline Reinforcement Learning from Vision Language Model Feedback20241