Related papers: Universal Few-Shot Spatial Control for Diffusion M…

Achieving generalizable and precise robotic manipulation across diverse environments remains a critical challenge, largely due to limitations in spatial perception. While prior imitation-learning approaches have made progress, their…

Diffusion models are a powerful class of generative models capable of producing high-quality images from pure noise using a simple text prompt. While most methods which introduce additional spatial constraints into the generated images…

Deep learning has achieved great success in video recognition, yet still struggles to recognize novel actions when faced with only a few examples. To tackle this challenge, few-shot action recognition methods have been proposed to transfer…

Diffusion models have shown remarkable results for image generation, editing and inpainting. Recent works explore diffusion models for 3D shape generation with neural implicit functions, i.e., signed distance function and occupancy…

Generalizing across robot embodiments and tasks is crucial for adaptive robotic systems. Modular policy learning approaches adapt to new embodiments but are limited to specific tasks, while few-shot imitation learning (IL) approaches often…

Diffusion models exhibit excellent sample quality, but existing guidance methods often require additional model training or are limited to specific tasks. We revisit guidance in diffusion models from the perspective of variational inference…

In order to quickly adapt to new data, few-shot learning aims at learning from few examples, often by using already acquired knowledge. The new data often differs from the previously seen data due to a domain shift, that is, a change of the…

Instruction-based image editing enables intuitive manipulation through natural language commands. However, text instructions alone often lack the precision required for fine-grained control over edit intensity. We introduce NumeriKontrol, a…

Learning high quality class representations from few examples is a key problem in metric-learning approaches to few-shot learning. To accomplish this, we introduce a novel architecture where class representations are conditioned for each…

Human beings can recognize new objects with only a few labeled examples, however, few-shot learning remains a challenging problem for machine learning systems. Most previous algorithms in few-shot learning only utilize spatial information…

Conditional image synthesis aims to create an image according to some multi-modal guidance in the forms of textual descriptions, reference images, and image blocks to preserve, as well as their combinations. In this paper, instead of…

We present MetaUVFS as the first Unsupervised Meta-learning algorithm for Video Few-Shot action recognition. MetaUVFS leverages over 550K unlabeled videos to train a two-stream 2D and 3D CNN architecture via contrastive learning to capture…

Diffusion models have demonstrated excellent performance in image generation. Although various few-shot semantic segmentation (FSS) models with different network structures have been proposed, performance improvement has reached a…

We present Readout Guidance, a method for controlling text-to-image diffusion models with learned signals. Readout Guidance uses readout heads, lightweight networks trained to extract signals from the features of a pre-trained, frozen…

Generating controllable character animation from a reference image and motion guidance remains a challenging task due to the inherent difficulty of injecting appearance and motion cues into video diffusion models. Prior works often rely on…

The objective of traffic prediction is to accurately forecast and analyze the dynamics of transportation patterns, considering both space and time. However, the presence of distribution shift poses a significant challenge in this field, as…

While impressive performance has been achieved in image captioning, the limited diversity of the generated captions and the large parameter scale remain major barriers to the real-word application of these systems. In this work, we propose…

Adapting a segmentation model from a labeled source domain to a target domain, where a single unlabeled datum is available, is one the most challenging problems in domain adaptation and is otherwise known as one-shot unsupervised domain…

While modern diffusion models excel at generating high-quality and diverse images, they still struggle with high-fidelity compositional and multimodal control, particularly when users simultaneously specify text prompts, subject references,…

Learning a universal policy across different robot morphologies can significantly improve learning efficiency and generalization in continuous control. However, it poses a challenging multi-task reinforcement learning problem, as the…