{"total":21,"rows":[{"id":"2603.05487","title":"Observing and Controlling Features in Vision-Language-Action Models","created":"2026-03-05","cited_by_count":16,"area":"vla"},{"id":"2603.19183","title":"Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Models","created":"2026-03-19","cited_by_count":16,"area":"vla"},{"id":"2603.19233","title":"Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Models","created":"2026-03-19","cited_by_count":15,"area":"vla"},{"id":"2512.11362","title":"An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges","created":"2025-12-12","cited_by_count":4,"area":"vla"},{"id":"2606.12299","title":"Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering","created":"2026-06-10","cited_by_count":4,"area":"vla"},{"id":"2608.13474","title":"Decoding Task Progress from VLA Representations","created":"2026-08-13","cited_by_count":3,"area":"vla"},{"id":"2605.00321","title":"Embodied Interpretability: Linking Causal Understanding to Generalization in Vision-Language-Action Models","created":"2026-05-01","cited_by_count":2,"area":"vla"},{"id":"2605.17204","title":"Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies","created":"2026-05-17","cited_by_count":2,"area":"vla"},{"id":"2607.14280","title":"DiMaS: Distribution Matching for Steering Vision-Language-Action Models","created":"2026-07-15","cited_by_count":1,"area":"vla"},{"id":"2606.00269","title":"Closed-Loop Neural Activation Control in Vision-Language-Action Models","created":"2026-05-29","cited_by_count":0,"area":"vla"},{"id":"2606.10495","title":"Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models","created":"2026-06-09","cited_by_count":0,"area":"vla"},{"id":"2608.16697","title":"FabriMAE I Trust Myself? Self-Evaluating VLA Action Generation with Markov Attention Entropy","created":"2026-08-17","cited_by_count":0,"area":"vla"},{"id":"2609.15005","title":"IMPACT-VLA: Interaction-aware Multimodal Propagation Attribution via Counterfactual Trajectories for Vision-Language-Action Policies","created":"2026-09-14","cited_by_count":0,"area":"vla"},{"id":"2609.28955","title":"ActGaze: Learning Action-Grounded Gaze through Counterfactual Visual Interventions for High-Precision Manipulation","created":"2026-09-24","cited_by_count":0,"area":"vla"},{"id":"2609.30996","title":"The Linear Representation Hypothesis for Vision-Language-Action Models","created":"2026-09-25","cited_by_count":0,"area":"vla"},{"id":"2609.31904","title":"GT-VLA: Target-Conditioned Trace Guidance for Generalizable Robotic Manipulation","created":"2026-09-25","cited_by_count":0,"area":"vla"},{"id":"2609.34599","title":"The Low-Rank Structure of VLA Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"vla"},{"id":"2609.34684","title":"Natural State-Prediction Accuracy can Hide Weak Controlled Responsiveness in VLA Readouts","created":"2026-09-28","cited_by_count":0,"area":"vla"},{"id":"2609.39971","title":"When Instructions Retrieve Trajectories: Diagnosing and Mitigating Generalization Failures in VLA Models","created":"2026-09-30","cited_by_count":0,"area":"vla"},{"id":"2610.00913","title":"eRLT: Efficient VLA Reinforcement Learning via Action-Relevant Token Routing","created":"2026-10-01","cited_by_count":0,"area":"vla"},{"id":"2610.03498","title":"Detect and Suppress: A Mechanistic Defense against Adversarial Patches in VLA Models","created":"2026-10-02","cited_by_count":0,"area":"vla"}],"next_cursor":null}