π0 and π0-FAST: Vision-Language-Action Models for General Robot Control

TS-Mask VLA: 2D Temporal-Spatial Masking for Vision-Language-Action Model with Effective Bridging

arXiv:2607. 09818v1 Announce Type: cross Abstract: Vision-language-action (VLA) models aim to understand natural-language instructions and visual observations, and to generate and execute corresponding actions as embodied agents.

MaskVLA: Visual Masking Against Trajectory Overfitting of Vision-Language-Action Model

arXiv:2609.23565v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models integrate vision-language understanding with executable robot actions, enabling end-to-end learning for robot contr...

See like a Robot: Robot-Centric Pointmaps for Vision-Language-Action Models

arXiv:2607. 11498v1 Announce Type: cross Abstract: Vision-language-action (VLA) models predict robot actions from visual observations and language instructions.

Contrastive Representation Regularization for Vision-Language-Action Models

arXiv:2510. 01711v4 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have shown strong capabilities in robot manipulation by leveraging rich representations from pre-trained Vision-Language Models (VLMs).

VLA-$\Delta$: Learning Physical State Transition for Vision-Language-Action Models

arXiv:2610.21306v1 Announce Type: new Abstract: Vision-language-action (VLA) models transfer semantic knowledge acquired through vision-language pretraining to robot control, achieving strong perform...

D$^2$-VLA: Dual-Memory Dual-Frequency Vision-Language-Action Model For Long Dynamic Manipulation

arXiv:2609.34792v2 Announce Type: replace Abstract: Long-horizon manipulation requires robots to remember cues that are no longer in view while responding to moving objects. Yet vision-language-actio...

Vision Language Models (Better, faster, stronger)

Measuring Language Transfer in Robot Policies: Adding Greek to a Cosmos3 Vision-Language-Action Policy

The paper investigates adding Greek language support to a Cosmos3 vision‑language‑action robot policy using only machine‑rephrased instructions and no architectural changes. It finds that many evaluation metrics can give misleading results, and that multilingual training with Greek yields a modest 6.7‑7.1 point advantage over a control, reaching about 40% of English performance. The study also shows that overfitting to a single translator’s phrasing can be mitigated by training on multiple phrasings, while warm‑starting from a language‑adapted world model or unfreezing the text tower actually harms performance.

Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens

arXiv:2610.01939v1 Announce Type: new Abstract: Vision language model (VLM) agents can control robots through visual feedback and action primitives, but repeated model invocations and redundant obser...

StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models

Vision-Language-Action (VLA) models have demonstrated effectiveness in robot manipulation, yet state-of-the-art models such as pi0.5 operate under a single-frame paradigm, limiting their ability to re...

Beyond Actions: Learning Future Operation Targets for Vision-Language-Action Models

The paper introduces Action–Future Coupled Effect Learning (AFCE), a method that shifts the primary prediction target of vision‑language‑action (VLA) policies from action chunks to future‑grounded physical Effects. AFCE constructs temporally ordered Effect tokens from demonstrations, robot responses, and visual transitions, and uses reconstruction objectives to preserve executable detail and physical change. On the DexJoCo benchmark, AFCE achieves a 50.97% overall success rate, outperforming baseline policies by 11.82 and 15.21 percentage points and excelling on all five bimanual tasks, underscoring the benefit of Effect supervision for coordinated dexterous manipulation.

AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention

arXiv:2511. 18960v4 Announce Type: replace Abstract: Vision-Language-Action (VLA) models have shown remarkable progress in embodied tasks recently, but most methods process visual observations independently at each timestep.