Zobrazeno 1 - 10
of 360
pro vyhledávání: '"Zhang, Weizhong"'
Current human image customization methods leverage Stable Diffusion (SD) for its rich semantic prior. However, since SD is not specifically designed for human-oriented generation, these methods often require extensive fine-tuning on large-scale datas
Externí odkaz:
http://arxiv.org/abs/2408.07433
Instruction tuning has achieved unprecedented success in NLP, turning large language models into versatile chatbots. However, the increasing variety and volume of instruction datasets demand significant computational resources. To address this, it is
Externí odkaz:
http://arxiv.org/abs/2407.15235
In contrast to moderate-size neural network pruning, structural weight pruning on the Large-Language Models (LLMs) imposes a novel challenge on the efficiency of the pruning algorithms, due to the heavy computation/memory demands of the LLMs. Recent
Externí odkaz:
http://arxiv.org/abs/2406.10576
Scene text synthesis involves rendering specified texts onto arbitrary images. Current methods typically formulate this task in an end-to-end manner but lack effective character-level guidance during training. Besides, their text encoders, pre-traine
Externí odkaz:
http://arxiv.org/abs/2405.14701
Publikováno v:
International Conference on Learning Representations (ICLR), 2024
We aim at exploiting additional auxiliary labels from an independent (auxiliary) task to boost the primary task performance which we focus on, while preserving a single task inference cost of the primary task. While most existing auxiliary learning m
Externí odkaz:
http://arxiv.org/abs/2405.05695
Cross-modal knowledge transfer enhances point cloud representation learning in LiDAR semantic segmentation. Despite its potential, the \textit{weak teacher challenge} arises due to repetitive and non-diverse car camera images and sparse, inaccurate g
Externí odkaz:
http://arxiv.org/abs/2405.04121
This paper presents a robust fine-tuning method designed for pre-trained 3D point cloud models, to enhance feature robustness in downstream fine-tuned models. We highlight the limitations of current fine-tuning methods and the challenges of learning
Externí odkaz:
http://arxiv.org/abs/2404.16422
PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering
Image composition involves seamlessly integrating given objects into a specific visual context. Current training-free methods rely on composing attention weights from several samplers to guide the generator. However, since these weights are derived f
Externí odkaz:
http://arxiv.org/abs/2403.05053
Out-of-distribution detection (OOD) is a crucial technique for deploying machine learning models in the real world to handle the unseen scenarios. In this paper, we first propose a simple yet effective Neural Activation Prior (NAP) for OOD detection.
Externí odkaz:
http://arxiv.org/abs/2402.18162
Ideal part editing should guarantee the diversity of edited parts, the fidelity to the remaining parts, and the quality of the results. However, previous methods do not disentangle each part completely, which means the edited parts will affect the ot
Externí odkaz:
http://arxiv.org/abs/2312.11867