Related papers: $\pi_{0.5}$: a Vision-Language-Action Model with O…

The rise of foundation models paves the way for generalist robot policies in the physical world. Existing methods relying on text-only instructions often struggle to generalize to unseen scenarios. We argue that interleaved image-text…

Despite the recent advancements of vision-language-action (VLA) models on a variety of robotics tasks, they suffer from critical issues such as poor generalizability to unseen tasks, due to their reliance on behavior cloning exclusively…

Vision-Language-Action (VLA) models have recently emerged, demonstrating strong generalization in robotic scene understanding and manipulation. However, when confronted with long-horizon tasks that require defined goal states, such as LEGO…

Fine-tuning vision-language models (VLMs) on robot teleoperation data to create vision-language-action (VLA) models is a promising paradigm for training generalist policies, but it suffers from a fundamental tradeoff: learning to produce…

Vision-language-action (VLA) models trained on large-scale internet data and robot demonstrations have the potential to serve as generalist robot policies. However, despite their large-scale training, VLAs are often brittle to…

In contrast to single-skill tasks, long-horizon tasks play a crucial role in our daily life, e.g., a pouring task requires a proper concatenation of reaching, grasping and pouring subtasks. As an efficient solution for transferring human…

Vision-Language-Action (VLA) models have emerged as a promising paradigm for robot learning, but their representations are still largely inherited from static image-text pretraining, leaving physical dynamics to be learned from…

A fundamental requirement for real-world robotic deployment is the ability to understand and respond to natural language instructions. Existing language-conditioned manipulation tasks typically assume that instructions are perfectly aligned…

Vision-Language-Action (VLA) models achieve over 95% success on standard benchmarks. However, through systematic experiments, we find that current state-of-the-art VLA models largely ignore language instructions. Prior work lacks: (1)…

Recent vision-language-action (VLA) models have significantly advanced robotic manipulation by unifying perception, reasoning, and control. To achieve such integration, recent studies adopt a predictive paradigm that models future visual…

Memory is critical for long-horizon and history-dependent robotic manipulation. Such tasks often involve counting repeated actions or manipulating objects that become temporarily occluded. Recent vision-language-action (VLA) models have…

Behavior cloning has shown promise for robot manipulation, but real-world demonstrations are costly to acquire at scale. While simulated data offers a scalable alternative, particularly with advances in automated demonstration generation,…

Vision-Language-Action (VLA) models have shown remarkable progress in embodied tasks recently, but most methods process visual observations independently at each timestep. This history-agnostic design treats robot manipulation as a Markov…

Domain generalization aims at training on source domains to uncover a domain-invariant feature space, allowing the model to perform robust generalization ability on unknown target domains. However, due to domain gaps, it is hard to find…

Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented capabilities and limited generalization across tasks, environments, and robot embodiments. In…

The deployment of artificial intelligence models at the edge is increasingly critical for autonomous robots operating in GPS-denied environments where local, resource-efficient reasoning is essential. This work demonstrates the feasibility…

Learning generalizable visual representations across different embodied environments is essential for effective robotic manipulation in real-world scenarios. However, the limited scale and diversity of robot demonstration data pose a…

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,…

Recent work on robot manipulation has advanced policy generalization to novel scenarios. However, it is often difficult to characterize how different evaluation settings actually represent generalization from the training distribution of a…

In recent years, instruction-tuned Large Multimodal Models (LMMs) have been successful at several tasks, including image captioning and visual question answering; yet leveraging these models remains an open question for robotics. Prior LMMs…