Related papers: SPA: 3D Spatial-Awareness Enables Effective Embodi…
Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potential to outperform the classical solutions developed for this…
Vision-Language-Action (VLA) models exhibit strong generalization in robotic manipulation, yet reinforcement learning (RL) fine-tuning often degrades robustness under spatial distribution shifts. For flow-matching VLA policies, this…
3D spatial understanding is essential in real-world applications such as robotics, autonomous vehicles, virtual reality, and medical imaging. Recently, Large Language Models (LLMs), having demonstrated remarkable success across various…
Episodic memory plays a crucial role in various cognitive processes, such as the ability to mentally recall past events. While cognitive science emphasizes the significance of spatial context in the formation and retrieval of episodic…
Several animal species (e.g., bats, dolphins, and whales) and even visually impaired humans have the remarkable ability to perform echolocation: a biological sonar used to perceive spatial layout and locate objects in the world. We explore…
Intelligent embodied agents (e.g. robots) need to perform complex semantic tasks in unfamiliar environments. Among many skills that the agents need to possess, building and maintaining a semantic map of the environment is most crucial in…
Despite impressive high-level video comprehension, multimodal language models struggle with spatial reasoning across time and space. While current spatial training approaches rely on real-world video data, obtaining diverse footage with…
We introduce SOMA, the Spatial Memory framework for Out-of-Vision Manipulation in Vision-Language-Action (VLA) models. Most existing VLAs implicitly assume that task-relevant objects are always visible, leading to brittle and reactive…
The complexity and diversity of surgical workflows, driven by heterogeneous operating room settings, institutional protocols, and anatomical variability, present a significant challenge in developing generalizable models for…
Current methods in training and benchmarking vision models exhibit an over-reliance on passive, curated datasets. Although models trained on these datasets have shown strong performance in a wide variety of tasks such as classification,…
In this work, we evaluate the effectiveness of representation learning approaches for decision making in visually complex environments. Representation learning is essential for effective reinforcement learning (RL) from high-dimensional…
Open-vocabulary 3D scene understanding presents a significant challenge in computer vision, with wide-ranging applications in embodied agents and augmented reality systems. Existing methods adopt neurel rendering methods as 3D…
Visual Foundation Models (VFMs), such as DINO and CLIP, excel in semantic understanding of images but exhibit limited spatial reasoning capabilities, which limits their applicability to embodied systems. As a result, recent work…
Deep learning models have achieved excellent recognition results on large-scale video benchmarks. However, they perform poorly when applied to videos with rare scenes or objects, primarily due to the bias of existing video datasets. We…
Current 3D-aware pretraining methods for embodied perception and manipulation are largely built on differentiable rendering frameworks, producing either fully implicit neural fields or fully explicit geometric primitives. Implicit…
The ability to update information acquired through various means online during task execution is crucial for a general-purpose service robot. This information includes geometric and semantic data. While SLAM handles geometric updates on 2D…
Recent trends in self-supervised representation learning have focused on removing inductive biases from training pipelines. However, inductive biases can be useful in settings when limited data are available or provide additional insight…
Embodied agents are expected to assist humans by actively exploring unknown environments and reasoning about spatial contexts. When deployed in real life, agents often face sequential tasks where each new task follows the completion of the…
The rapid growth of digital pathology and advances in self-supervised deep learning have enabled the development of foundational models for various pathology tasks across diverse diseases. While multimodal approaches integrating diverse…
Embodied AI models often employ off the shelf vision backbones like CLIP to encode their visual observations. Although such general purpose representations encode rich syntactic and semantic information about the scene, much of this…