HölderPO unifies token-level aggregation in GRPO via the Hölder mean with a tunable p parameter and annealing schedule, delivering 54.9% average accuracy on math benchmarks and 93.8% success on ALFWorld.
hub
arXiv preprint arXiv:2506.08440 , year=
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
PDF improves VLA success rates on LIBERO and Atari by applying test-time perturbation learning with delayed feedback to correct trajectory overfitting and overconfidence.
E-VLA integrates event streams directly into VLA models via lightweight fusion, raising Pick-Place success from 0% to 60-90% at 20 lux and from 0% to 20-25% under severe motion blur.
A dual-tower 4D embodied world model called RoboStereo reduces geometric hallucinations and delivers over 97% relative improvement on manipulation tasks via test-time augmentation, imitative learning, and open exploration.
RISE combines a controllable dynamics model and progress value model into a closed-loop self-improving pipeline that updates robot policies entirely in imagination, reporting over 35% absolute gains on three real-world tasks.
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.
SimpleVLA-RL applies tailored reinforcement learning to VLA models, reaching SoTA on LIBERO, outperforming π₀ on RoboTwin, and surpassing SFT in real-world tasks while reducing data needs and identifying a 'pushcut' phenomenon.
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 is a two-stage optimization framework for cross-task scaling of Vision-Language-Action models via dynamic grouped residual optimization in RL.
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.
citing papers explorer
-
Holder Policy Optimisation
HölderPO unifies token-level aggregation in GRPO via the Hölder mean with a tunable p parameter and annealing schedule, delivering 54.9% average accuracy on math benchmarks and 93.8% success on ALFWorld.
-
Test-Time Perturbation Learning with Delayed Feedback for Vision-Language-Action Models
PDF improves VLA success rates on LIBERO and Atari by applying test-time perturbation learning with delayed feedback to correct trajectory overfitting and overconfidence.
-
E-VLA: Event-Augmented Vision-Language-Action Model for Dark and Blurred Scenes
E-VLA integrates event streams directly into VLA models via lightweight fusion, raising Pick-Place success from 0% to 60-90% at 20 lux and from 0% to 20-25% under severe motion blur.
-
RoboStereo: Dual-Tower 4D Embodied World Models for Unified Policy Optimization
A dual-tower 4D embodied world model called RoboStereo reduces geometric hallucinations and delivers over 97% relative improvement on manipulation tasks via test-time augmentation, imitative learning, and open exploration.
-
RISE: Self-Improving Robot Policy with Compositional World Model
RISE combines a controllable dynamics model and progress value model into a closed-loop self-improving pipeline that updates robot policies entirely in imagination, reporting over 35% absolute gains on three real-world tasks.
-
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.
-
SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
SimpleVLA-RL applies tailored reinforcement learning to VLA models, reaching SoTA on LIBERO, outperforming π₀ on RoboTwin, and surpassing SFT in real-world tasks while reducing data needs and identifying a 'pushcut' phenomenon.
-
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.
-
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.
- LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization