CORTEXA
← Browse
arxivcs.ROcs.LG2026-07-07

Pelican-VLA 0.5: Attending Before Acting Benefits Generalization

Zeyuan Ding, Wenhai Liu, Yang Xu, Jiayu Hu, Yinda Chen, Yi Zhang, Yong Dai, Jian Tang, Xiaozhu Ju

In this report, we present Pelican-VLA 0.5, a unified VLA model that integrates vision-language understanding, future-frame generation, and action prediction within a single architecture. Pelican-VLA 0.5 achieves attention-level generalization: without object annotations, segmentation masks, attention supervision, or task-specific fine-tuning, its action pathway already focuses on the manipulation-relevant object and contact region. This behavior persists across unseen scenes and unseen robot embodiments, and is substantially stronger than in other open-source VLA baselines. We verify that this ability originates from the learnable Bottleneck Token inserted between perception and action: by routing task-relevant visual information through a compact bottleneck, the tokens interface induces manipulation-centric attention during pre-training and remains effective across different policy structures, including a MoT-style architecture.

View free PDFSource page

Related papers

arxivcs.ROcs.CVcs.LG2026-07-07

Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement

Ryuji Oi, Hikari Otsuka, Kosuke Matsushima, Yuki Ichikawa, Masato Motomura, Tatsuya Kaneko, et al.

Vision-Language-Action (VLA) models have emerged as a promising approach for generalizable robotic manipulations. In particular, flow matching-based VLA models have shown remarkable success due to their capability to generate precise and smooth action sequences and capture multim…

View free PDFSource page
arxivcs.ROcs.AIcs.LG2026-07-15

Never Too Late for Force: Accelerating VLA Post-Training with Reactive Force Injection

Yi Wang, Wendi Chen, Zimo Wen, Han Xue, Xueqi Li, Wenye Yu, et al.

Pretrained vision-language-action (VLA) policies provide strong language-conditioned manipulation knowledge, but they remain largely vision-driven and can struggle once manipulation enters contact states where the scene is occluded, depth is ambiguous, or small force errors push…

View free PDFSource page
arxivcs.ROcs.LG2026-07-17

Foresight Residual RL for Long-Horizon Robot Manipulation with Vision-Language-Action Models

Yuhan Liu, Xinyu Zhang, Litao Liu, Abdeslam Boularias

Vision-Language-Action (VLA) policies offer strong general-purpose manipulation priors, but often fail on tight-tolerance, contact-rich assembly due to long-horizon credit assignment and subtask coupling: a state that is geometrically successful for the current skill can be britt…

View free PDFSource page
arxivcs.ROcs.AIcs.CRcs.LG2026-07-20

Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models

Tuan Duong Trinh, Naveed Akhtar, Basim Azam

Does adding a reasoning step make a Vision-Language-Action (VLA) model more robust to perturbation? Intuitively, a policy that reasons before acting should absorb a perturbed input better than one that maps observations directly to actions. We test this premise head-on across thr…

View free PDFSource page
arxivcs.ROcs.LG2026-07-05

XS-VLA: Coupling Coarse-grained Spatial Distillation with Latent Flow Matching for Lightweight Robotic Control

Lei Iok Tong, Qingchen Xie, Wei Huang, Ying Jie Yap, Yujie Zhang, Qianzhi Li, et al.

Large Vision-Language Models (LVLMs) have shown strong multimodal understanding and spatial grounding, but their computational cost limits real-time robotic control. In contrast, lightweight models are suitable for edge deployment but often suffer from "spatial blindness", namely…

View free PDFSource page
arxivcs.ROcs.LG2026-07-20

Patch Policy: Efficient Embodied Control via Dense Visual Representations

Gaoyue Zhou, Zichen Jeff Cui, Ada Langford, Bowen Tan, Yann LeCun, Lerrel Pinto

Pretrained dense visual features from Vision Transformers (ViTs) are powerful yet have been underutilized in robot learning. Modern robot policies either compress each observation into a single global token, or rely on visual backbones trained from scratch, sacrificing both fine-…

View free PDFSource page