Related papers: DINOv3-Diffusion Policy: Self-Supervised Large Vis…

We study how to transfer representations pretrained on source tasks to target tasks in visual percept based RL. We analyze two popular approaches: freezing or finetuning the pretrained representations. Empirical studies on a set of popular…

Fully-supervised category-level pose estimation aims to determine the 6-DoF poses of unseen instances from known categories, requiring expensive mannual labeling costs. Recently, various self-supervised category-level pose estimation…

Extreme low-data fine-grained classification is common in expert domains where labeling is expensive, yet practitioners still need principled guidance for selecting pretrained encoders. We study emerald inclusion grading with a custom…

Diffusion models (DMs) have emerged as powerful foundation models for a variety of tasks, with a large focus in synthetic image generation. However, their requirement of large annotated datasets for training limits their applicability in…

Diffusion strategies have advanced visual motor control by progressively denoising high-dimensional action sequences, providing a promising method for robot manipulation. However, as task complexity increases, the success rate of existing…

The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision. These models could greatly simplify the use of images in any…

Diffusion Transformers (DiTs) excel at visual generation yet remain hampered by slow sampling. Existing training-free accelerators - step reduction, feature caching, and sparse attention - enhance inference speed but typically rely on a…

2D visual foundation models, such as DINOv3, a self-supervised model trained on large-scale natural images, have demonstrated strong zero-shot generalization, capturing both rich global context and fine-grained structural cues. However, an…

Vision-Language-Action (VLA) models adapt large vision-language backbones to map images and instructions into robot actions. However, prevailing VLAs either generate actions auto-regressively in a fixed left-to-right order or attach…

In the context of imitation learning, visuomotor-based diffusion policy learning is one of the main directions in robotic manipulation. Most of these approaches rely on point clouds as observation inputs and construct scene representations…

Visuomotor policy learning has witnessed substantial progress in robotic manipulation, with recent approaches predominantly relying on generative models to model the action distribution. However, these methods often overlook the critical…

Self-supervised visual foundation models produce powerful embeddings that achieve remarkable performance on a wide range of downstream tasks. However, unlike vision-language models such as CLIP, self-supervised visual features are not…

Recent self-supervised Vision Transformers (ViTs), such as DINOv3, provide rich feature representations for dense vision tasks. This study investigates the intrinsic few-shot semantic segmentation (FSS) capabilities of frozen DINOv3…

Recent breakthroughs in self-supervised learning have enabled the use of large unlabeled datasets to train visual foundation models that can generalize to a variety of downstream tasks. While this training paradigm is well suited for the…

This paper introduces a novel approach to leverage features learned from both supervised and self-supervised paradigms, to improve image classification tasks, specifically for vehicle classification. Two state-of-the-art self-supervised…

Robotic manipulation tasks often rely on static cameras for perception, which can limit flexibility, particularly in scenarios like robotic surgery and cluttered environments where mounting static cameras is impractical. Ideally, robots…

Diffusion policies are powerful visuomotor models for robotic manipulation, yet they often fail to generalize to manipulators or end-effectors unseen during training and struggle to accommodate new task requirements at inference time.…

Diffusion models have emerged as state-of-the-art generative methods for image synthesis, yet their potential as general-purpose feature encoders remains underexplored. Trained for denoising and generation without labels, they can be…

Vision-based imitation learning has enabled impressive robotic manipulation skills, but its reliance on object appearance while ignoring the underlying 3D scene structure leads to low training efficiency and poor generalization. To address…

Data availability remains a critical bottleneck in many deep learning applications. Large-scale datasets are often expensive to collect, curate and annotate, which can limit the scalability and applicability of supervised learning methods.…