T^2VLA is a test-time reinforcement learning framework for VLAs that uses internal confidence to define intrinsic rewards via similarity to high-confidence expert demonstrations and a dual-expert bootstrapping mechanism.
arXiv preprint arXiv:2512.02834 , year=
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 8roles
background 1polarities
background 1representative citing papers
E-TTS introduces a plug-and-play test-time scaling method for embodied tasks that unifies reasoning-action sampling with history buffers and closed-loop refinement to improve performance on manipulation benchmarks.
ZPRL adapts frozen flow-matching imitation policies via RL perturbations on a task-relevant bottleneck latent, yielding 33.7% higher average success on four real-world manipulation tasks than action-residual baselines.
COAST applies contrastive conceptors to steer VLA hidden states into task-specific success subspaces, yielding over 20% simulation and 40% real-robot success rate gains across three distinct policies.
A retrieve-then-steer method stores successful robot actions in memory and uses them to steer a frozen VLA's flow-matching sampler for better test-time reliability without parameter updates.
PRTS pretrains VLA models with contrastive goal-conditioned RL to embed goal-reachability probabilities from offline data, yielding SOTA results on robotic benchmarks especially for long-horizon and novel instructions.
TapSampling improves generalist robotic manipulation policies at inference time via latent action sampling with an Action-VAE and selection by a task-progress outcome predictor.
A structured literature survey of safety mechanisms in long-horizon robotic manipulation organized by intervention timing and strength of supporting evidence.
citing papers explorer
-
Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models
T^2VLA is a test-time reinforcement learning framework for VLAs that uses internal confidence to define intrinsic rewards via similarity to high-confidence expert demonstrations and a dual-expert bootstrapping mechanism.
-
E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation
E-TTS introduces a plug-and-play test-time scaling method for embodied tasks that unifies reasoning-action sampling with history buffers and closed-loop refinement to improve performance on manipulation benchmarks.
-
Beyond Action Residuals: Real-World Robot Policy Steering via Bottleneck Latent Reinforcement Learning
ZPRL adapts frozen flow-matching imitation policies via RL perturbations on a task-relevant bottleneck latent, yielding 33.7% higher average success on four real-world manipulation tasks than action-residual baselines.
-
Contrastive Conceptor Activation Steering (COAST): Unlocking Vision-Language-Action Models through Hidden States
COAST applies contrastive conceptors to steer VLA hidden states into task-specific success subspaces, yielding over 20% simulation and 40% real-robot success rate gains across three distinct policies.
-
Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs
A retrieve-then-steer method stores successful robot actions in memory and uses them to steer a frozen VLA's flow-matching sampler for better test-time reliability without parameter updates.
-
PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations
PRTS pretrains VLA models with contrastive goal-conditioned RL to embed goal-reachability probabilities from offline data, yielding SOTA results on robotic benchmarks especially for long-horizon and novel instructions.
-
TapSampling: Inference-Time Sampling with a Task-Progress-Understanding Verifier for Robotic Manipulation
TapSampling improves generalist robotic manipulation policies at inference time via latent action sampling with an Action-VAE and selection by a task-progress outcome predictor.
-
Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation
A structured literature survey of safety mechanisms in long-horizon robotic manipulation organized by intervention timing and strength of supporting evidence.