LIBERO-Safety supplies a scalable benchmark, data-generation pipeline, and 19,664-demonstration dataset that exposes a generalization-safety tension in current VLA models where diverse training improves collision avoidance but task success stays limited by trajectory quality and semantic understandi
hub Canonical reference
Interactive Post-Training for Vision-Language-Action Models
Canonical reference. 90% of citing Pith papers cite this work as background.
38
Pith papers citing it
Background
90% of classified citations
abstract
We introduce RIPT-VLA, a simple and scalable reinforcement-learning-based interactive post-training paradigm that fine-tunes pretrained Vision-Language-Action (VLA) models using only sparse binary success rewards. Existing VLA training pipelines rely heavily on offline expert demonstration data and supervised imitation, limiting their ability to adapt to new tasks and environments under low-data regimes. RIPT-VLA addresses this by enabling interactive post-training with a stable policy optimization algorithm based on dynamic rollout sampling and leave-one-out advantage estimation. RIPT-VLA has the following characteristics. First, it applies to various VLA models, resulting in an improvement on the lightweight QueST model by 21.2%, and the 7B OpenVLA-OFT model to an unprecedented 97.5% success rate. Second, it is computationally efficient and data-efficient: with only one demonstration, RIPT-VLA enables an unworkable SFT model (4%) to succeed with a 97% success rate within 15 iterations. Furthermore, we demonstrate that the policy learned by RIPT-VLA generalizes across different tasks and scenarios and is robust to the initial state context. These results highlight RIPT-VLA as a practical and effective paradigm for post-training VLA models through minimal supervision.
hub tools
citation-role summary
background 9
baseline 1
citation-polarity summary
representative citing papers
PCM uses success-failure action variance to probabilistically select and mask chunks for gradient updates in GRPO, matching standard success rates with 2.38x wall-clock speedup and 60% lower memory on LIBERO benchmarks.
MoLA infers a mixture of latent actions from generated future videos via modality-aware inverse dynamics models to improve robot manipulation policies.
MCF-Proto adds a motion-centric local action frame and prototype parameterization to VLA models, inducing emergent geometric structure and improved robustness from standard demonstrations alone.
VLAFlow shows that combining language-supervised co-training with future latent alignment produces the most stable transfer performance for vision-language-action models trained on mixed robot data.
Introduces H-Tac human tactile-action dataset and TTP pre-training that unifies spaces and predicts future tactile signals to improve robotic dexterous manipulation transfer.
Aligning temporal granularity, action subspaces, and train-test conditioning yields SOTA long-horizon mobile and fine-grained manipulation success for a unified world-action model.
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.
dVLA-RL models denoising as an MDP to enable RL on dVLAs via trajectory probabilities, reporting 99.7% success on LIBERO and 30.6% gains over SFT on RoboTwin 2.0.
GAM splits a geometric foundation model to enable language-conditioned future geometry prediction and action decoding for robot policies, claiming superior performance on manipulation benchmarks.
APT pretrains the action expert as a vision-action prior on frozen VLM features then adds language through gated fusion to improve OOD instruction generalization in continuous-action VLA policies.
MPCoT improves long-horizon VLA performance on LIBERO and CALVIN by initializing M latent hypotheses, refining them over K steps, and aggregating via a reward-trained path scorer while preserving the original 8-step action interface and generating zero reasoning tokens.
ELAN4D introduces plug-and-play 4D keypoint track supervision from forward kinematics to enhance VLA policy generalization in robotic manipulation tasks.
3DVLA is a plug-and-play framework that enhances pretrained VLAs with pervasive 3D feature encoding using multi-view consistency and Spatially-Conditioned Geometry Aggregation, an instance estimation module, and a masked self-supervised 3D branch, yielding gains on LIBERO-Plus and RoboTwin 2.0.
Afford-VLA internalizes task-conditioned affordance as an explicit visual planning interface within VLA models via learnable <AFF> tokens, achieving SOTA on LIBERO and SimplerEnv benchmarks.
GuidedVLA improves VLA generalization by supervising individual attention heads with manually defined auxiliary signals for three task-relevant factors.
By inverting a frozen flow-matching robot policy with fixed-point iteration, UniSteer converts human corrections into noise-space supervision and lifts real-world VLA adaptation success from 20% to 90% in about 66 minutes on average.
Anchor-Centric Adaptation escapes the diversity trap by prioritizing repeated demonstrations at core anchors over broad coverage, yielding higher success rates under fixed data budgets in robotic manipulation.
LWD is a fleet-scale offline-to-online RL framework that continually improves pretrained VLA policies using autonomous rollouts and human interventions, reaching 95% average success on real-world manipulation tasks.
LaST-R1 introduces a RL post-training method called LAPO that optimizes latent Chain-of-Thought reasoning in vision-language-action models, yielding 99.9% success on LIBERO and up to 22.5% real-world gains.
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.
ABot-M0 unifies heterogeneous robot data into a 6-million-trajectory dataset and introduces Action Manifold Learning to predict stable actions on a low-dimensional manifold using a DiT backbone.
LifeLong-RFT applies chunking-level on-policy reinforcement learning with Quantized Action Consistency Reward, Continuous Trajectory Alignment Reward, and Format Compliance Reward to fine-tune VLA models, achieving a 22% average success rate gain over supervised fine-tuning on the LIBERO benchmark's
TwinRL expands RL exploration via digital twin reconstruction and twin RL warm-up to guide real-world learning, reaching near-100% success with 20 minutes of on-robot time across four tasks.
citing papers explorer
-
LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Models
LIBERO-Safety supplies a scalable benchmark, data-generation pipeline, and 19,664-demonstration dataset that exposes a generalization-safety tension in current VLA models where diverse training improves collision avoidance but task success stays limited by trajectory quality and semantic understandi
-
Learn Where Outcomes Diverge: Efficient VLA RL via Probabilistic Chunk Masking
PCM uses success-failure action variance to probabilistically select and mask chunks for gradient updates in GRPO, matching standard success rates with 2.38x wall-clock speedup and 60% lower memory on LIBERO benchmarks.
-
From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation
MoLA infers a mixture of latent actions from generated future videos via modality-aware inverse dynamics models to improve robot manipulation policies.
-
Beyond World-Frame Action Heads: Motion-Centric Action Frames for Vision-Language-Action Models
MCF-Proto adds a motion-centric local action frame and prototype parameterization to VLA models, inducing emergent geometric structure and improved robustness from standard demonstrations alone.
-
VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment
VLAFlow shows that combining language-supervised co-training with future latent alignment produces the most stable transfer performance for vision-language-action models trained on mixed robot data.
-
Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation
Introduces H-Tac human tactile-action dataset and TTP pre-training that unifies spaces and predicts future tactile signals to improve robotic dexterous manipulation transfer.
-
ABot-M0.5: Unified Mobility-and-Manipulation World Action Model
Aligning temporal granularity, action subspaces, and train-test conditioning yields SOTA long-horizon mobile and fine-grained manipulation success for a unified world-action model.
-
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.
-
dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models
dVLA-RL models denoising as an MDP to enable RL on dVLAs via trajectory probabilities, reporting 99.7% success on LIBERO and 30.6% gains over SFT on RoboTwin 2.0.
-
Geometric Action Model for Robot Policy Learning
GAM splits a geometric foundation model to enable language-conditioned future geometry prediction and action decoding for robot policies, claiming superior performance on manipulation benchmarks.
-
APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
APT pretrains the action expert as a vision-action prior on frozen VLM features then adds language through gated fusion to improve OOD instruction generalization in continuous-action VLA policies.
-
MPCoT: Reward-Guided Multi-Path Latent Reasoning for Test-Time Scalable Vision-Language-Action
MPCoT improves long-horizon VLA performance on LIBERO and CALVIN by initializing M latent hypotheses, refining them over K steps, and aggregating via a reward-trained path scorer while preserving the original 8-step action interface and generating zero reasoning tokens.
-
ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptation
ELAN4D introduces plug-and-play 4D keypoint track supervision from forward kinematics to enhance VLA policy generalization in robotic manipulation tasks.
-
3DVLA: Enhancing Vision-Language-Action Models via 3D Spatial and Instance Understanding
3DVLA is a plug-and-play framework that enhances pretrained VLAs with pervasive 3D feature encoding using multi-view consistency and Spatially-Conditioned Geometry Aggregation, an instance estimation module, and a masked self-supervised 3D branch, yielding gains on LIBERO-Plus and RoboTwin 2.0.
-
Afford-VLA: Action-Aligned Visual Planning via Internalized Affordance
Afford-VLA internalizes task-conditioned affordance as an explicit visual planning interface within VLA models via learnable <AFF> tokens, achieving SOTA on LIBERO and SimplerEnv benchmarks.
-
GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization
GuidedVLA improves VLA generalization by supervising individual attention heads with manually defined auxiliary signals for three task-relevant factors.
-
UniSteer: Unified Noise Steering for Efficient Human-Guided VLA Adaptation
By inverting a frozen flow-matching robot policy with fixed-point iteration, UniSteer converts human corrections into noise-space supervision and lifts real-world VLA adaptation success from 20% to 90% in about 66 minutes on average.
-
Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation
Anchor-Centric Adaptation escapes the diversity trap by prioritizing repeated demonstrations at core anchors over broad coverage, yielding higher success rates under fixed data budgets in robotic manipulation.
-
Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies
LWD is a fleet-scale offline-to-online RL framework that continually improves pretrained VLA policies using autonomous rollouts and human interventions, reaching 95% average success on real-world manipulation tasks.
-
LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning
LaST-R1 introduces a RL post-training method called LAPO that optimizes latent Chain-of-Thought reasoning in vision-language-action models, yielding 99.9% success on LIBERO and up to 22.5% real-world gains.
-
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.
-
ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning
ABot-M0 unifies heterogeneous robot data into a 6-million-trajectory dataset and introduces Action Manifold Learning to predict stable actions on a low-dimensional manifold using a DiT backbone.
-
Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning
LifeLong-RFT applies chunking-level on-policy reinforcement learning with Quantized Action Consistency Reward, Continuous Trajectory Alignment Reward, and Format Compliance Reward to fine-tune VLA models, achieving a 22% average success rate gain over supervised fine-tuning on the LIBERO benchmark's
-
TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation
TwinRL expands RL exploration via digital twin reconstruction and twin RL warm-up to guide real-world learning, reaching near-100% success with 20 minutes of on-robot time across four tasks.
-
$\pi^{*}_{0.6}$: a VLA That Learns From Experience
RECAP enables a generalist VLA to self-improve via advantage-conditioned RL on mixed real-world data, more than doubling throughput and halving failure rates on hard manipulation tasks.
-
World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
World-Env replaces physical robot interactions with a world model-based virtual environment and VLM-guided rewards to enable efficient RL post-training for VLA models, showing gains with only five demonstrations per task.
-
FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation
FORCE is a 3-stage RL fine-tuning method for VLA models that stabilizes Q-function via on-policy warm-up and filters high-value actions for updates, claiming 79% success rate gains and 32.5% faster training without human intervention.
-
TacCoRL: Integrating Tactile Feedback into VLA via Simulation
TacCoRL integrates tactile feedback into VLA policies via real-aligned simulation co-training and RL, raising average success from 50% to 72.5% on four bimanual contact-rich tasks with direct real-robot transfer.
-
MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models
MemoryVLA++ integrates a perceptual-cognitive memory bank and denoising world model into VLA models to enable temporal reasoning, yielding performance gains on manipulation benchmarks and real-robot tasks.
-
RoVLA: Multi-Consistency Constraints for Robust Vision-Language-Action Models
RoVLA enforces instructional, evolutionary, and observational consistency to improve robustness of VLA policies on manipulation benchmarks and real robots.
-
PAPO-VLA: Planning-Aware Policy Optimization for Vision-Language-Action Models
PAPO-VLA identifies planning actions via variation and outcome, estimates their causal importance, and folds that importance into GRPO to emphasize key decisions while still using full-trajectory feedback.
-
DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization
DyGRO-VLA is a two-stage optimization framework for cross-task scaling of Vision-Language-Action models via dynamic grouped residual optimization in RL.
-
Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulation
The method uses multi-view diffusion priors and action manifold learning to resolve depth ambiguity and improve action prediction in VLA robotic manipulation models, reporting higher success rates than baselines on LIBERO, RoboTwin, and real-robot tasks.
-
VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts
VLA-GSE uses spectral decomposition of the VLA backbone to create generalized and specialized experts, enabling effective robot task adaptation while updating only 2.51% of parameters and achieving 81.2% zero-shot success on LIBERO-Plus.
-
VGAS: Value-Guided Action-Chunk Selection for Few-Shot Vision-Language-Action Adaptation
VGAS uses best-of-N selection with a geometrically grounded critic and explicit regularization to improve success rates of few-shot VLA policies under limited data and distribution shifts.
-
AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention
AVA-VLA reformulates VLA learning as a POMDP using recurrent states and active visual attention to achieve state-of-the-art results on LIBERO, CALVIN, and real dual-arm tasks.
-
Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey
This survey organizes large VLM-based VLA models for robotic manipulation into monolithic and hierarchical paradigms, reviews their integrations and datasets, and outlines future directions.
-
EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models
EXPO-FT enables pretrained VLA policies to reach 30/30 success on complex manipulation tasks using an average of 19.1 minutes of online robot data while outperforming prior RL approaches.