Instruction Generalization in VLAs

VLA: Vision-Language-Action Model

Overview

Vision-language-action models must connect a command to what they see and then choose actions, even when wording, objects, locations, or task combinations differ from training. Researchers test this with paraphrase and language-variation benchmarks such as LIBERO-Para, as well as held-out object–location pairings and real-robot tasks. Approaches include synthetic instruction augmentation, counterfactual training, explicit grounding and subgoal planning, and test-time guidance. These methods can improve robustness, but models still show brittle language grounding and visual shortcuts; greater responsiveness to instructions does not always mean better task success or transfer to harder commands.

Latest papers

CardsList

46 papers5 papers in the last four weeks, down 69% on the four weeks before. 0.0% of all new papers.

  1. CoBoVLA: Decoupling Language from Action with Discrete Codes for Robust and Interpretable Robot Manipulation

    Nov 17, 2026Mehul Arora, Dhruv Agarwal, Ambuj AgrawalVision-Language-Action ModelsInstruction Generalization in VLAs

  2. BURGER: Benchmarking and Understanding Robotic Generalization via Embodied Drawing

    Oct 29, 2026Xiangyu Xu, Bangshuai Peng, Ziyi Liu +5Instruction Generalization in VLAsVision-Language-Action Models

  3. Cartender: Verifiable Language-Conditioned Driving by Learning the Drives Not Taken

    Oct 19, 2026Zhiwen Chen, Benjin Zhu, Yan Xie +1Instruction Generalization in VLAsTrajectory Generation

  4. Robotic Photography System based on Vision-Language-Action Model

    Oct 19, 2026Song-Li Wu, Chubin Zhang, Wenbo Ding +1Vision-Language-Action ModelsInstruction Generalization in VLAs

  5. Same Goal, Different Words: Spatial Instruction Sensitivity in World-Action Models

    Oct 12, 2026Ali-Adeeb Abbas, Esmaeil Seraj, Behrad Toghi +1World Model EvaluationVision-Language-Action Models

  6. VioLA: Learning Generalist Humanoid Control Policies from Human Data

    Oct 8, 2026Mert Albaba, Jens Beißwenger, Anna Manasyan +6Humanoid Robot ControlRobot Imitation Learning

  7. Many Ways to Succeed: Diversity-Driven RL Fine-Tuning for VLA Generalization

    Oct 7, 2026Haoru Li, Jinmei Liu, Zhiyong Wang +5Robot Policy GeneralizationRL Fine-Tuning

  8. TempoBridge: Language-Guided Tempo Control for Vision-Language-Action Policies

    Oct 7, 2026Yeonseo Lee, Hyosup Shin, Guebin Hwang +1Language-Conditioned Robot ControlVision-Language-Action Models

  9. OGAM: Connecting Systematic Testing to Runtime Assurance through Object-Grounded Attention Monitoring for VLA Policies

    Oct 5, 2026Haki Darwish, Xiangyu Yin, Changwen Li +3Failure Detection for VLAsInstruction Generalization in VLAs

  10. MixVLA: Adaptive Mixing of Non-Invariant Information for Generalizable Vision-Language-Action Models

    Oct 2, 2026Pingrui Zhang, Yu Zhang, Pengyuan Wu +8OOD Generalization in VLAsVision-Language-Action Models

  11. Same Scene, Different Task: Skill Alignment for Compositional Generalization in VLAs

    Sep 30, 2026Taegeun Yang, Youngju Na, Yoonki Cho +1Vision-Language-Action ModelsCounterfactual Data Augmentation

  12. When Instructions Retrieve Trajectories: Diagnosing and Mitigating Generalization Failures in VLA Models

    Sep 30, 2026Hung-Jen Chen, Yu-Hsun Hou, Yan-Hong Chen +4Robotic ManipulationVision-Language-Action Models

  13. Disentangling Spurious Correlations in Vision-Language-Action Models via Predicting Domain-Invariant Latent Lookahead

    Sep 29, 2026Junghyun Kim, Ngseo Kim, ChungWoo Lee +7Domain GeneralizationVision-Language-Action Models

  14. LexiconVLA: Learning Reusable Atomic Action Codebooks for Unseen Tasks

    Sep 29, 2026Zeming Wei, Jianheng Ye, Xinshuai Song +3Visuomotor Policy LearningRobotic Manipulation

  15. Reasoning Without Inference Cost: Latent Semantic Scaffolding for Robot VLA Policies

    Sep 4, 2026Andrew Ting Yan Li, Zhuo Li, Zhelin Yang +3Reasoning for VLAsVision-Language-Action Models

  16. DeicticVLA: Unifying Instruction Modes Based on Language and Deictic Gestures in a Single VLA

    Aug 28, 2026Kango Yanagida, Tatsuya Aoki, Yuichiro Yoshikawa +1Vision-Language-Action ModelsInstruction Generalization in VLAs

  17. MA-VLA: Multi-Arm Vision-Language-Action Model for Collaboration and Compositional Generalization

    Aug 26, 2026Zaibin Zhang, Junlan Xiao, Zhongbo Zhang +11Vision-Language-Action ModelsInstruction Generalization in VLAs

  18. Fine-Tuning VLAs with Self-Demonstrated Generative Control for Multi-Task Manipulation

    Aug 19, 2026Prachi Garg, Steve Xing, Prahit Yaugand +2Robot LearningVision-Language-Action Models

  19. AWM-VLA: AlignedWorld Modeling for Efficient and Explainable Vision-Language-Action Policies

    Aug 15, 2026An Lanji, Dawei Liu, Jin Li +3World Models for VLAsVision-Language-Action Models