Related papers: GLaD: Geometric Latent Distillation for Vision-Lan…

VLA models encode visual observations as 2D patch tokens with no intrinsic geometric structure. We introduce GST-VLA with two contributions. First, the Gaussian Spatial Tokenizer (GST) converts frozen dense depth and frozen semantic patch…

Vision-Language-Action (VLA) models provide a promising paradigm for robot learning by integrating visual perception with language-guided policy learning. However, most existing approaches rely on 2D visual inputs to perform actions in 3D…

We propose CLAD -- a Constrained Latent Action Diffusion model for vision-language procedure planning in instructional videos. Procedure planning is the challenging task of predicting intermediate actions given a visual observation of a…

Spatial perception and reasoning are crucial for Vision-Language-Action (VLA) models to accomplish fine-grained manipulation tasks. However, existing approaches often lack the ability to understand and reason over the essential 3D…

Recent Vision-Language-Action (VLA) models have made impressive progress toward general-purpose robotic manipulation by post-training large Vision-Language Models (VLMs) for action prediction. Yet most VLAs entangle perception and control…

Despite significant progress in Vision-Language Navigation (VLN), existing approaches still rely on dense RGB videos that produce excessive patch tokens and lack explicit spatial structure, resulting in substantial computational overhead…

Latent action representations learned from unlabeled videos have recently emerged as a promising paradigm for pretraining vision-language-action (VLA) models without explicit robot action supervision. However, latent actions derived solely…

The scarcity of large-scale 3D-text paired data poses a great challenge on open vocabulary 3D scene understanding, and hence it is popular to leverage internet-scale 2D data and transfer their open vocabulary capabilities to 3D models…

Large-scale 3D vision-language models (VLMs) like LLaVA-3D offer strong spatial reasoning but are difficult to deploy due to high computational costs. We propose a knowledge distillation framework that transfers spatial reasoning from a 7B…

Language-guided grasping has emerged as a promising paradigm for enabling robots to identify and manipulate target objects through natural language instructions, yet it remains highly challenging in cluttered or occluded scenes. Existing…

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in 2D visual tasks but still exhibit limited physical spatial awareness when processing real-world visual streams. Recently, feed-forward geometric foundation…

Multimodal Large Language Models (MLLMs) demonstrate exceptional semantic reasoning but struggle with 3D spatial perception when restricted to pure RGB inputs. Despite leveraging implicit geometric priors from 3D reconstruction models,…

Leveraging diverse robotic data for pretraining remains a critical challenge. Existing methods typically model the dataset's action distribution using simple observations as inputs. However, these inputs are often incomplete, resulting in a…

Vision-Language-Action (VLA) models aim to control robots for manipulation from visual observations and natural-language instructions. However, existing hierarchical and autoregressive paradigms often introduce architectural overhead,…

Billion-parameter Vision-Language-Action (VLA) policies have recently shown impressive performance in robotic manipulation, yet their size and inference cost remain major obstacles for real-time closed-loop control. We introduce…

Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. Furthermore, they perform action prediction by learning a direct mapping from perception to action,…

Vision-Language-Action (VLA) models achieve strong generalization in robotic manipulation but remain largely reactive and 2D-centric, making them unreliable in tasks that require precise 3D reasoning. We propose GeoPredict, a geometry-aware…

Equipping embodied agents with the ability to reason about tasks, foresee physical outcomes, and generate precise actions is essential for general-purpose manipulation. While recent Vision-Language-Action (VLA) models have leveraged…

Recent advancements in open-source Visual Language Models (VLMs) such as LLaVA, Qwen-VL, and Llama have catalyzed extensive research on their integration with diverse systems. The internet-scale general knowledge encapsulated within these…

We introduce OG-VLA, a novel architecture and learning framework that combines the generalization strengths of Vision Language Action models (VLAs) with the robustness of 3D-aware policies. We address the challenge of mapping natural…