EBench is a benchmark that evaluates generalist mobile manipulation policies on 26 tasks across 5 capability and 4 generalization dimensions, revealing distinct capability profiles among models with similar success rates.
StarVLA-$\alpha$: Reducing Complexity in Vision-Language-Action Systems
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for building general-purpose robotic agents. However, the VLA landscape remains highly fragmented and complex: as existing approaches vary substantially in architectures, training data, embodiment configurations, and benchmark-specific engineering. In this work, we introduce StarVLA-$\alpha$, a simple yet strong baseline designed to study VLA design choices under controlled conditions. StarVLA-$\alpha$ deliberately minimizes architectural and pipeline complexity to reduce experimental confounders and enable systematic analysis. Specifically, we re-evaluate several key design axes, including action modeling strategies, robot-specific pretraining, and interface engineering. Across unified multi-benchmark training on LIBERO, SimplerEnv, RoboTwin, and RoboCasa, the same simple baseline remains highly competitive, indicating that a strong VLM backbone combined with minimal design is already sufficient to achieve strong performance without relying on additional architectural complexity or engineering tricks. Notably, our single generalist model outperforms $\pi_{0.5}$ by 20\% on the public real-world RoboChallenge benchmark. We expect StarVLA-$\alpha$ to serve as a solid starting point for future research in the VLA regime. Code will be released at https://github.com/starVLA/starVLA.
years
2026 6verdicts
UNVERDICTED 6representative citing papers
Discrete diffusion policies act as natural asynchronous executors for robotics by treating action generation as iterative unmasking, yielding higher success rates and lower computation than flow-matching real-time chunking in dynamic tasks.
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.
A 3D-thinking-guided co-training method disentangles geometry perception and spatial reasoning to inject latent 3D priors into VLA models via adapters, achieving SOTA on manipulation benchmarks while running on 2D images only.
SPARC generates reliable spatial annotations for robot demonstrations by leveraging spatio-temporal task structure, outperforming detection baselines on localization accuracy while retaining more samples and enabling competitive model performance without manual annotations.
Efficient-WAM delivers 30x lower latency than prior WAMs at 100 ms per chunk while keeping competitive manipulation performance by treating coarse future video as guidance rather than high-fidelity output.
citing papers explorer
-
EBench: Elemental Diagnosis of Generalist Mobile Manipulation Policies
EBench is a benchmark that evaluates generalist mobile manipulation policies on 26 tasks across 5 capability and 4 generalization dimensions, revealing distinct capability profiles among models with similar success rates.
-
DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors
Discrete diffusion policies act as natural asynchronous executors for robotics by treating action generation as iterative unmasking, yielding higher success rates and lower computation than flow-matching real-time chunking in dynamic tasks.
-
SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale
SPARC generates reliable spatial annotations for robot demonstrations by leveraging spatio-temporal task structure, outperforming detection baselines on localization accuracy while retaining more samples and enabling competitive model performance without manual annotations.
-
Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination
Efficient-WAM delivers 30x lower latency than prior WAMs at 100 ms per chunk while keeping competitive manipulation performance by treating coarse future video as guidance rather than high-fidelity output.