The paper introduces NEO-VLA, an encoder‑free vision‑language‑action framework that tokenizes images with lightweight patch convolutions and lets visual and language features evolve together throughout the backbone. By allowing a flow‑matching action expert to access instruction‑conditioned visual representations at multiple depths, NEO‑VLA consistently outperforms encoder‑based counterparts across diverse manipulation tasks and distribution shifts. Layer‑wise probing reveals that action‑critical signals peak early in the visual hierarchy, underscoring the benefit of accessing representations across the computational pipeline rather than relying on a fixed encoder output.
arXiv:2609.06079v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies leverage pretrained vision-language models (VLMs) to guide action generation for robot control. VLMs provide hier...
V-Link is a method designed to enhance Vision‑Language‑Action (VLA) models by recovering visual representations during the transfer from vision‑language (VL) features to action (A) features. It introduces complementary Spatial and Semantic Query representations that are injected into Action DiT through asymmetric pathways, providing both semantic augmentation and dedicated geometric conditioning for action generation. Experiments on LIBERO, LIBERO‑Plus, RoboTwin 2.0, and real‑world AGIBOT A3 Ultra tasks show significant performance gains over the base GR00T N1.6 model.
arXiv:2601. 03309v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models, which integrate pretrained large Vision-Language Models (VLM) into their policy backbone, are gaining significant attention for their promising generalization capabilities.
arXiv:2606. 20246v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models pre-trained on massive video-robot datasets have revolutionized robotic manipulation, yet their multi-billion parameter architectures impose prohibitive computational burdens during downstream fine-tuning and real-time inference.
arXiv:2609.38616v1 Announce Type: cross Abstract: While Vision-Language-Action (VLA) models enable flexible action generation, their generalization across diverse environmental elements, including ma...
The paper introduces BAS‑VLA, a task‑semantic action calibration framework for vision‑language‑action models that addresses two failure modes: unnecessary action drift under appearance changes and insufficient behavioral change under semantic alterations. BAS‑VLA uses a breaking‑centered calibration core and a selective evidence‑gated preserving auxiliary to maintain performance on clean and semantics‑preserving conditions while suppressing stale‑task behavior. Experiments on OpenPI‑pi0.5 and LIBERO‑Object Milk‑Swap show high success rates on clean and preserved tasks, a dramatic drop under target‑object swaps, and improved robustness to style shifts from 42% to 70% without harming clean performance.
RawVLA introduces a streaming neural image signal processor that adaptively renders RAW observations for vision‑language‑action (VLA) policies, focusing on imaging factors that influence embodied behavior. The authors systematically analyze how five ISP dimensions—gain, sensor noise, chromatic response, tonal response, and bit depth—affect action prediction and manipulation success, showing that RAW‑to‑RGB processing significantly shapes outcomes. They also present RawVLA‑Bench, a RAW‑domain manipulation benchmark that evaluates image processing as an explicit variable across clean and adverse conditions, demonstrating that RawVLA maintains performance under standard settings while markedly improving robustness under degraded imaging.
arXiv:2605. 22183v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for generalist robotic manipulation.
arXiv:2606.18363v3 Announce Type: replace-cross Abstract: Language models trained on large-scale vision-language data have demonstrated strong potential for embodied agents. Harnessing models through...
DynamicVLA is a latency‑aware Vision‑Language‑Action model designed for dynamic object manipulation, featuring a compact 0.4B architecture and a convolutional vision encoder for efficient multimodal inference. It employs a continuous inference schedule that overlaps reasoning and execution, and a Latent‑aware Action Streaming mechanism that discards stale action prefixes to maintain action‑time alignment. The authors also introduce the Dynamic Object Manipulation (DOM) benchmark, comprising 200K synthetic episodes and 2K real‑world episodes, and demonstrate that DynamicVLA improves dynamic manipulation success in simulation and on real robots.
The paper introduces STAR (Steering Action Representations), a training‑free inference technique for vision‑language‑action models that addresses a late‑layer grounding gap. STAR applies an exponential moving average over late‑layer residual updates, enabling later action representations to inherit object‑aware update directions from earlier layers without changing the model. By incorporating recent proprioceptive states to adjust mixing strength, STAR improves object awareness in late layers and boosts average task success rates by 4.0 percentage points on robot manipulation benchmarks.
arXiv:2607. 14635v1 Announce Type: new Abstract: Action supervision in vision-language-action (VLA) models is often treated as a downstream objective for learning action prediction.