# Language-conditioned policies and VLAs

Area: [Offline RL and imitation learning from data](https://mlsanity.com/offlinerl/index.md). HTML: https://mlsanity.com/offlinerl/language-conditioned-policies-and-vlas/

## Key facts

- Language-conditioned policies and VLAs: 162 papers on arXiv since 2018 (data through 14 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).
- 8 new papers 17 Sep–14 Oct.

## Most cited here

- [Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation](https://mlsanity.com/paper/1811.10092/) (2018), cited by 8 papers here
- [Language-Conditioned Imitation Learning for Robot Manipulation Tasks](https://mlsanity.com/paper/2010.12083/) (2020), cited by 5 papers here
- [Offline RL for Natural Language Generation with Implicit Language Q Learning](https://mlsanity.com/paper/2206.11871/) (2022), cited by 4 papers here
- [Offline Reinforcement Learning for Visual Navigation](https://mlsanity.com/paper/2212.08244/) (2022), cited by 4 papers here
- [Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning](https://mlsanity.com/paper/1812.03509/) (2018), cited by 3 papers here
- [Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog](https://mlsanity.com/paper/1907.00456/) (2019), cited by 3 papers here
- [Language Conditioned Imitation Learning over Unstructured Data](https://mlsanity.com/paper/2005.07648/) (2020), cited by 3 papers here
- [What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Data](https://mlsanity.com/paper/2204.06252/) (2022), cited by 3 papers here
- [Model-Based Runtime Monitoring with Interactive Imitation Learning](https://mlsanity.com/paper/2310.17552/) (2023), cited by 3 papers here
- [Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning](https://mlsanity.com/paper/2405.15624/) (2024), cited by 3 papers here

## New (17 Sep–14 Oct)

- [Value-Preserving Action Quantization](https://mlsanity.com/paper/2610.17252/) (2026-10-12)
- [Trust-Calibrated VLA Policy Post-Training with Evolving Imagination](https://mlsanity.com/paper/2610.16517/) (2026-10-12)
- [Dream to Remember: Continual Steering of Generalist Robot Policies with World Models](https://mlsanity.com/paper/2610.13816/) (2026-10-09)
- [Iterative Policy Refinement through Semantic Rollout Analysis](https://mlsanity.com/paper/2610.01652/) (2026-10-01)
- [Does Continual Imitation Learning Remain Grounded? A Language-Perturbed Benchmark for Robotic Task Retention](https://mlsanity.com/paper/2610.00542/) (2026-09-30)
- [Looking Back to Move Forward: Temporal Verification for Generative Robot Policies](https://mlsanity.com/paper/2609.39038/) (2026-09-30)
- [Multi-Granularity Language-Guided Imitation Learning via Instruction Decomposition](https://mlsanity.com/paper/2609.37135/) (2026-09-29)
- [Towards VLA-Dreamer: Refining VLA Behavior Using World Models](https://mlsanity.com/paper/2609.31313/) (2026-09-25)