Deep Learning
Learning 1D Causal Visual Representation with De-focus Attention Networks Chenxin Tao
While images typically require 2D non-causal modeling, texts utilize 1D causal modeling.
Archaeoscape: Bringing Aerial Laser Scanning Archaeology to the Deep Learning Era
However, the lack of expert-annotated, open-access resources has hindered the analysis of ALS data using advanced deep learning techniques.
Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling
Our study reveals the roles of critical parameters in the Transformer, such as the number of layers and the number of attention heads.
Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model
Despite the significant achievements of Vision Transformers (ViTs) in various vision tasks, they are constrained by the quadratic complexity.
Geometric Trajectory Diffusion Models
With global translation or rotation applied to a trajectory of molecular dynamics, the entire trajectory still describes the same dynamics and the generative model should estimate the same likelihood.
AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation
Pre-trained vision-language models (VLMs) have shown impressive results in various visual classification tasks.
