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.
Vla-r1: Enhancing rea- soning in vision-language-action models
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
other 1
citation-polarity summary
years
2026 10representative citing papers
Reducing visual input to one token per frame in VLA world models maintains or improves long-horizon performance on MetaWorld, LIBERO, and real-robot tasks.
KinDER is a new open-source benchmark that demonstrates substantial gaps in current robot learning and planning methods for handling physical constraints.
Repurposing a VLA’s vision encoder to emit one action-supervised memory token per historical frame-view yields long-horizon manipulation with large success gains and low latency.
CoLT replaces text chain-of-thought in multimodal LLMs with three supervised latent vectors, improving average accuracy from 75.7 to 79.1 across eight benchmarks while cutting text-decoding time 22.6x.
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.
Layer analysis of DINOv3 shows non-uniform 3D geometric knowledge concentrated in deeper layers, enabling a last-layer-centric recombination module that improves monocular depth estimation accuracy to state-of-the-art levels.
GeoWorld applies hyperbolic geometry to JEPA world models and introduces geometric reinforcement learning, reporting modest success-rate gains of ~3% and ~2% on 3- and 4-step planning tasks versus V-JEPA 2.
DIAL expands continuous-action driving policies via intent-conditioned flow matching and multi-intent GRPO, lifting best-of-N preference scores above human demonstrations for the first time on WOD-E2E.
EG-GRPO augments VLA aerial navigation with expert-guided group relative policy optimization and a faster simulation pipeline, claiming 2.13x success rate and 60.9% better intent alignment versus SFT baseline.
citing papers explorer
-
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.
-
One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy
Reducing visual input to one token per frame in VLA world models maintains or improves long-horizon performance on MetaWorld, LIBERO, and real-robot tasks.
-
KinDER: A Physical Reasoning Benchmark for Robot Learning and Planning
KinDER is a new open-source benchmark that demonstrates substantial gaps in current robot learning and planning methods for handling physical constraints.
-
NativeMEM: Native Memory Compression for Long-Horizon Robotic Manipulation
Repurposing a VLA’s vision encoder to emit one action-supervised memory token per historical frame-view yields long-horizon manipulation with large success gains and low latency.
-
CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts
CoLT replaces text chain-of-thought in multimodal LLMs with three supervised latent vectors, improving average accuracy from 75.7 to 79.1 across eight benchmarks while cutting text-decoding time 22.6x.
-
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.
-
Last-Layer-Centric Feature Recombination: Unleashing 3D Geometric Knowledge in DINOv3 for Monocular Depth Estimation
Layer analysis of DINOv3 shows non-uniform 3D geometric knowledge concentrated in deeper layers, enabling a last-layer-centric recombination module that improves monocular depth estimation accuracy to state-of-the-art levels.
-
GeoWorld: Geometric World Models
GeoWorld applies hyperbolic geometry to JEPA world models and introduces geometric reinforcement learning, reporting modest success-rate gains of ~3% and ~2% on 3- and 4-step planning tasks versus V-JEPA 2.
-
Driving Intents Amplify Planning-Oriented Reinforcement Learning
DIAL expands continuous-action driving policies via intent-conditioned flow matching and multi-intent GRPO, lifting best-of-N preference scores above human demonstrations for the first time on WOD-E2E.
-
Towards Precise Intent-Aligned VLA Aerial Navigation via Expert-Guided GRPO
EG-GRPO augments VLA aerial navigation with expert-guided group relative policy optimization and a faster simulation pipeline, claiming 2.13x success rate and 60.9% better intent alignment versus SFT baseline.