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. Grounded Semantic Re-Binding for Robust Instruction Generalization in Vision-Language-Action Models

    Aug 3, 2026Zhaokai Yin, Zhipeng ZhangVision-Language GroundingVision-Language-Action Models

  2. Pelican-VLA 0.5: Attending Before Acting Benefits Generalization

    Jul 7, 2026Zeyuan Ding, Wenhai Liu, Yang Xu +6Next-Action PredictionGeneralization in Robotic Manipulation

  3. APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies

    Jun 10, 2026Kechun Xu, Zhenjie Zhu, Anzhe Chen +2Visuomotor Policy LearningVision-Language-Action Models

  4. DISC: Decoupling Instruction from State-Conditioned Control via Policy Generation

    May 20, 2026Hanxiang Ren, Pei Zhou, Xunzhe Zhou +1Language-Conditioned Robot ManipulationVisuomotor Policy Learning

  5. LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models

    Mar 30, 2026Chanyoung Kim, Minwoo Kim, Minseok Kang +2Vision-Language GroundingVision-Language-Action Models

  6. Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Models

    Mar 19, 2026Aiden Swann, Lachlain McGranahan, Hugo Buurmeijer +2Vision-Language-Action ModelsInstruction Generalization in VLAs

  7. Red-Teaming Vision-Language-Action Models via Quality Diversity Prompt Generation for Robust Robot Policies

    Mar 12, 2026Siddharth Srikanth, Freddie Liang, Ya-Chuan Hsu +9Robustness of VLAsAdversarial Attacks on VLAs

  8. See, Plan, Rewind: Progress-Aware Vision-Language-Action Models for Robust Robotic Manipulation

    Mar 10, 2026Tingjun Dai, Mingfei Han, Tingwen Du +6Vision-Language-Action ModelsLanguage-Conditioned Robot Manipulation

  9. LangGap: Diagnosing and Closing the Language Gap in Vision-Language-Action Models

    Feb 28, 2026Yuchen Hou, Lin ZhaoVision-Language-Action ModelsInstruction Generalization in VLAs