Related papers: Viewpoint-Agnostic Manipulation Policies with Stra…
The diversity, quantity, and quality of manipulation data are critical for training effective robot policies. However, due to hardware and physical setup constraints, collecting large-scale real-world manipulation data remains difficult to…
In robotics, Vision-Language-Action (VLA) models that integrate diverse multimodal signals from multi-view inputs have emerged as an effective approach. However, most prior work adopts static fusion that processes all visual inputs…
360-degree panoramic videos have gained considerable attention in recent years due to the rapid development of head-mounted displays (HMDs) and panoramic cameras. One major problem in streaming panoramic videos is that panoramic videos are…
Appearance-based gaze estimation has been actively studied in recent years. However, its generalization performance for unseen head poses is still a significant limitation for existing methods. This work proposes a generalizable multi-view…
Several factors contribute to the appearance of an object in a visual scene, including pose, illumination, and deformation, among others. Each factor accounts for a source of variability in the data, while the multiplicative interactions of…
The effectiveness of scaling up training data in robotic manipulation is still limited. A primary challenge in manipulation is the tasks are diverse, and the trained policy would be confused if the task targets are not specified clearly.…
We study how to generalize the visuomotor policy of a mobile manipulator from the perspective of visual observations. The mobile manipulator is prone to occlusion owing to its own body when only a single viewpoint is employed and a…
Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing policies overlook one or both. They typically rely on 2D visual observations and backbones pretrained…
In recent years, several unsupervised, "contrastive" learning algorithms in vision have been shown to learn representations that perform remarkably well on transfer tasks. We show that this family of algorithms maximizes a lower bound on…
We study view-invariant imitation learning by explicitly conditioning policies on camera extrinsics. Using Plucker embeddings of per-pixel rays, we show that conditioning on extrinsics significantly improves generalization across viewpoints…
Visual Question Answering (VQA) models employ attention mechanisms to discover image locations that are most relevant for answering a specific question. For this purpose, several multimodal fusion strategies have been proposed, ranging from…
The performance of image-based Reinforcement Learning (RL) agents can vary depending on the position of the camera used to capture the images. Training on multiple cameras simultaneously, including a first-person egocentric camera, can…
We propose a viewpoint invariant model for 3D human pose estimation from a single depth image. To achieve this, our discriminative model embeds local regions into a learned viewpoint invariant feature space. Formulated as a multi-task…
Event-based cameras are dynamic vision sensors that provide asynchronous measurements of changes in per-pixel brightness at a microsecond level. This makes them significantly faster than conventional frame-based cameras, and an appealing…
On-policy knowledge distillation has proven effective for language models, yet its application to vision-language models (VLMs) remains underexplored. We observe that standard on-policy distillation can improve a student's output quality…
Vision-Language-Action (VLA) models have shown promise in robot manipulation but often struggle to generalize to new instructions or complex multi-task scenarios. We identify a critical pathology in current training paradigms where…
Neural network-based visuomotor policies enable robots to perform manipulation tasks but remain susceptible to perceptual attacks. For example, conventional 2D adversarial patches are effective under fixed-camera setups, where appearance is…
Route planning for navigation under partial observability plays a crucial role in modern robotics and autonomous driving. Existing route planning approaches can be categorized into two main classes: traditional autoregressive and…
Autonomous inspection in hazardous environments requires AI agents that can interpret high-level goals and execute precise control. A key capability for such agents is spatial grounding, for example when a drone must center a detected…
Many recent approaches in representation learning implicitly assume that uncorrelated views of a data point are sufficient to learn meaningful representations for various downstream tasks. In this work, we challenge this assumption and…