mlsanityData to 7 Oct 2026

Vision-language-action models

13 directions · 1,509 papers · 36 this week

Busiest this week

Most new since Mon 5 Oct

Failure recovery and robustness

109 papers5 this weekMedium confidence in this grouping: mostly one topic, with blurry edgesMedium confidence in this grouping: mostly one topic, with blurry edges · About

  1. Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models
  2. Beyond Reconstruction: What Matters in Action Tokenization for Robot Policies?
  3. CARE: Certifying Acceleration for Vision-Language-Action Inference
  4. Adapting Vision-Language-Action Models to Unknown Visual Disruptions During Execution
  5. When to Switch: Reliable Action-Chunk Extension for Vision-Language-Action Models
Open →

All directions

Largest first · week from Mon 5 Oct

  1. Generalist VLA models and benchmarksvla, vision-language-action, robot, roboticMedium confidence in this grouping: mostly one topic, with blurry edges · About2760Medium confidence in this grouping: mostly one topic, with blurry edges
  2. Efficient VLA inference and adaptationaction, vla, inference, vision-language-actionHigh confidence in this grouping: the papers form one clear topic · About2374High confidence in this grouping: the papers form one clear topic
  3. Reinforcement learning and post-trainingvla, policy, reinforcement, reinforcement learningHigh confidence in this grouping: the papers form one clear topic · About1734High confidence in this grouping: the papers form one clear topic
  4. Reasoning and chain-of-thought in VLAreasoning, memory, vla, manipulationMedium confidence in this grouping: mostly one topic, with blurry edges · About1371Medium confidence in this grouping: mostly one topic, with blurry edges
  5. 3D and spatial-aware VLAspatial, manipulation, vla, actionHigh confidence in this grouping: the papers form one clear topic · About1290High confidence in this grouping: the papers form one clear topic
  6. Failure recovery and robustnessfailure, vla, manipulation, vision-language-actionMedium confidence in this grouping: mostly one topic, with blurry edges · About1095Medium confidence in this grouping: mostly one topic, with blurry edges
  7. Human-video and latent-action pretrainingaction, human, robot, latentHigh confidence in this grouping: the papers form one clear topic · About1032High confidence in this grouping: the papers form one clear topic
  8. VLA for autonomous drivingdriving, autonomous driving, autonomous, reasoningHigh confidence in this grouping: the papers form one clear topic · About1011High confidence in this grouping: the papers form one clear topic
  9. World model-based VLAaction, visual, modeling, latentHigh confidence in this grouping: the papers form one clear topic · About763High confidence in this grouping: the papers form one clear topic
  10. Safety and adversarial attackssafety, attacks, attack, adversarialHigh confidence in this grouping: the papers form one clear topic · About581High confidence in this grouping: the papers form one clear topic
  11. Tactile, force-aware and humanoid VLAtactile, contact-rich, force, manipulationHigh confidence in this grouping: the papers form one clear topic · About501High confidence in this grouping: the papers form one clear topic
  12. VLA architectures and generalizationvla, action, visual, vision-language-actionHigh confidence in this grouping: the papers form one clear topic · About433High confidence in this grouping: the papers form one clear topic
  13. Aerial and drone VLAaerial, navigation, uav, onboardHigh confidence in this grouping: the papers form one clear topic · About171High confidence in this grouping: the papers form one clear topic
10 new this week aren’t in a direction yet
  1. Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models
  2. SpikingVLA: Asynchronous Spiking Vision-Language-Action Models
  3. SMART: Zero-Shot Sim-to-Real Articulated Object Manipulation via Large-Scale Synthetic Pretraining
  4. BiGym 2.0: Benchmarking Learned and Agent-Developed Policies for Humanoid Household Manipulation
  5. Seeing the Invisible: Physics-Guided Visual Prompting for Temperature- and Radiation-Aware VLA Navigation
  6. Wiring Matters: Injection Topology and Initialization of Affordance Heads in Vision-Language-Action Policies
  7. Arm-wise Compositional Generalization in Dual-Arm Vision-Language-Action Models
  8. OGAM: Connecting Systematic Testing to Runtime Assurance through Object-Grounded Attention Monitoring for VLA Policies
  9. What the Guard Misses, the Robot Executes: Implied Harm in VLA Instructions
  10. Demonstration-Calibrated Port-Hamiltonian Retuning for Manipulation Policies

Weekly activity

Papers per week, 22 Jun – 5 Oct (last week partial)

  1. DirectionConfidencepapers16 wks
  2. Efficient VLA inference and adaptationHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 22 Jun: 7; 29 Jun: 4; 6 Jul: 6; 13 Jul: 6; 20 Jul: 0; 27 Jul: 7; 3 Aug: 6; 10 Aug: 6; 17 Aug: 2; 24 Aug: 5; 31 Aug: 2; 7 Sep: 7; 14 Sep: 12; 21 Sep: 5; 28 Sep: 17; 5 Oct: 423796
  3. Failure recovery and robustnessMedium confidence in this grouping: mostly one topic, with blurry edges · AboutMedium confidence in this grouping: mostly one topic, with blurry edgesPer week: 22 Jun: 2; 29 Jun: 3; 6 Jul: 1; 13 Jul: 1; 20 Jul: 2; 27 Jul: 2; 3 Aug: 6; 10 Aug: 2; 17 Aug: 3; 24 Aug: 4; 31 Aug: 8; 7 Sep: 0; 14 Sep: 8; 21 Sep: 8; 28 Sep: 17; 5 Oct: 510972
  4. Reinforcement learning and post-trainingHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 22 Jun: 5; 29 Jun: 5; 6 Jul: 4; 13 Jul: 3; 20 Jul: 0; 27 Jul: 4; 3 Aug: 2; 10 Aug: 5; 17 Aug: 5; 24 Aug: 6; 31 Aug: 1; 7 Sep: 2; 14 Sep: 9; 21 Sep: 11; 28 Sep: 11; 5 Oct: 417377
  5. World model-based VLAHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 22 Jun: 2; 29 Jun: 2; 6 Jul: 2; 13 Jul: 1; 20 Jul: 0; 27 Jul: 1; 3 Aug: 2; 10 Aug: 4; 17 Aug: 1; 24 Aug: 2; 31 Aug: 4; 7 Sep: 3; 14 Sep: 0; 21 Sep: 3; 28 Sep: 12; 5 Oct: 37642
  6. Generalist VLA models and benchmarksMedium confidence in this grouping: mostly one topic, with blurry edges · AboutMedium confidence in this grouping: mostly one topic, with blurry edgesPer week: 22 Jun: 6; 29 Jun: 8; 6 Jul: 4; 13 Jul: 5; 20 Jul: 2; 27 Jul: 0; 3 Aug: 2; 10 Aug: 6; 17 Aug: 3; 24 Aug: 3; 31 Aug: 3; 7 Sep: 3; 14 Sep: 7; 21 Sep: 4; 28 Sep: 6; 5 Oct: 027662
  7. Reasoning and chain-of-thought in VLAMedium confidence in this grouping: mostly one topic, with blurry edges · AboutMedium confidence in this grouping: mostly one topic, with blurry edgesPer week: 22 Jun: 1; 29 Jun: 1; 6 Jul: 4; 13 Jul: 0; 20 Jul: 2; 27 Jul: 2; 3 Aug: 7; 10 Aug: 4; 17 Aug: 1; 24 Aug: 7; 31 Aug: 4; 7 Sep: 1; 14 Sep: 1; 21 Sep: 4; 28 Sep: 10; 5 Oct: 113750
  8. 3D and spatial-aware VLAHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 22 Jun: 6; 29 Jun: 3; 6 Jul: 3; 13 Jul: 2; 20 Jul: 0; 27 Jul: 2; 3 Aug: 10; 10 Aug: 1; 17 Aug: 1; 24 Aug: 3; 31 Aug: 3; 7 Sep: 1; 14 Sep: 4; 21 Sep: 4; 28 Sep: 6; 5 Oct: 012949
  9. VLA architectures and generalizationHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 22 Jun: 0; 29 Jun: 2; 6 Jul: 0; 13 Jul: 1; 20 Jul: 0; 27 Jul: 0; 3 Aug: 0; 10 Aug: 0; 17 Aug: 1; 24 Aug: 1; 31 Aug: 1; 7 Sep: 1; 14 Sep: 1; 21 Sep: 5; 28 Sep: 5; 5 Oct: 34321
  10. Human-video and latent-action pretrainingHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 22 Jun: 3; 29 Jun: 3; 6 Jul: 3; 13 Jul: 0; 20 Jul: 0; 27 Jul: 1; 3 Aug: 4; 10 Aug: 2; 17 Aug: 1; 24 Aug: 2; 31 Aug: 3; 7 Sep: 1; 14 Sep: 6; 21 Sep: 3; 28 Sep: 2; 5 Oct: 210336
  11. Tactile, force-aware and humanoid VLAHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 22 Jun: 3; 29 Jun: 2; 6 Jul: 0; 13 Jul: 1; 20 Jul: 2; 27 Jul: 2; 3 Aug: 1; 10 Aug: 1; 17 Aug: 2; 24 Aug: 0; 31 Aug: 1; 7 Sep: 0; 14 Sep: 5; 21 Sep: 1; 28 Sep: 6; 5 Oct: 15028
  12. VLA for autonomous drivingHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 22 Jun: 3; 29 Jun: 4; 6 Jul: 2; 13 Jul: 2; 20 Jul: 1; 27 Jul: 1; 3 Aug: 3; 10 Aug: 4; 17 Aug: 3; 24 Aug: 0; 31 Aug: 3; 7 Sep: 0; 14 Sep: 5; 21 Sep: 2; 28 Sep: 3; 5 Oct: 110137
  13. Safety and adversarial attacksHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 22 Jun: 3; 29 Jun: 1; 6 Jul: 0; 13 Jul: 2; 20 Jul: 0; 27 Jul: 2; 3 Aug: 1; 10 Aug: 2; 17 Aug: 1; 24 Aug: 0; 31 Aug: 1; 7 Sep: 1; 14 Sep: 3; 21 Sep: 2; 28 Sep: 4; 5 Oct: 15824
  14. Aerial and drone VLAHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 22 Jun: 0; 29 Jun: 1; 6 Jul: 1; 13 Jul: 1; 20 Jul: 0; 27 Jul: 0; 3 Aug: 0; 10 Aug: 1; 17 Aug: 1; 24 Aug: 0; 31 Aug: 1; 7 Sep: 0; 14 Sep: 0; 21 Sep: 0; 28 Sep: 2; 5 Oct: 1179