相关论文: Inducing Spatial Locality in Vision Transformers t…

Despite achieving remarkable performance on various vision-language tasks, Transformer-based Vision-Language Models (VLMs) suffer from redundancy in inputs and parameters, significantly hampering their efficiency in real-world applications.…

The identification of hazardous driving behaviors from in-cabin video streams is essential for enhancing road safety and supporting the detection of traffic violations and unsafe driver actions. However, current temporal action localization…

In-context Learning (ICL) utilizes structured demonstration-query inputs to induce few-shot learning on Language Models (LMs), which are not originally pre-trained on ICL-style data. To bridge the gap between ICL and pre-training, some…

Recently, window-based attention methods have shown great potential for computer vision tasks, particularly in Single Image Super-Resolution (SISR). However, it may fall short in capturing long-range dependencies and relationships between…

The recent surge in video generation has shown the growing demand for high-quality video synthesis using large vision models. Existing video generation models are predominantly based on the video diffusion transformer (vDiT), however, they…

Recent work in interpretability shows that large language models (LLMs) can be adapted for new tasks in a learning-free way: it is possible to intervene on LLM representations to elicit desired behaviors for alignment. For instance, adding…

Grounding textual phrases in visual content is a meaningful yet challenging problem with various potential applications such as image-text inference or text-driven multimedia interaction. Most of the current existing methods adopt the…

The paper proposes an efficient structure for enhancing the performance of mobile-friendly vision transformer with small computational overhead. The vision transformer (ViT) is very attractive in that it reaches outperforming results in…

Vision transformers (ViTs) that model an image as a sequence of partitioned patches have shown notable performance in diverse vision tasks. Because partitioning patches eliminates the image structure, to reflect the order of patches, ViTs…

Vision Transformers have attracted a lot of attention recently since the successful implementation of Vision Transformer (ViT) on vision tasks. With vision Transformers, specifically the multi-head self-attention modules, networks can…

This paper investigates the role of CLIP image embeddings within the Stable Video Diffusion (SVD) framework, focusing on their impact on video generation quality and computational efficiency. Our findings indicate that CLIP embeddings,…

Map-free LiDAR localization systems accurately localize within known environments by predicting sensor position and orientation directly from raw point clouds, eliminating the need for large maps and descriptors. However, their long…

Vision Transformers (ViTs) have shown strong empirical performance on high-dimensional medical imaging data, yet their behavior under survival objectives and the interpretability of their attention mechanisms remain poorly understood. Under…

Visual attention mechanisms have proven to be integrally important constituent components of many modern deep neural architectures. They provide an efficient and effective way to utilize visual information selectively, which has shown to be…

Vision Transformer (ViT) has shown high potential in video recognition, owing to its flexible design, adaptable self-attention mechanisms, and the efficacy of masked pre-training. Yet, it remains unclear how to adapt these pre-trained…

In this work, we propose Visual-Predictive Instruction Tuning (VPiT) - a simple and effective extension to visual instruction tuning that enables a pretrained LLM to quickly morph into an unified autoregressive model capable of generating…

Efficient Visual Instruction Fine-Tuning (EVIT) seeks to adapt Multimodal Large Language Models (MLLMs) to downstream tasks with minimal computational overhead. However, as task diversity and complexity increase, EVIT faces significant…

This work presents a systematic investigation into modernizing Vision Transformer backbones by leveraging architectural advancements from the past five years. While preserving the canonical Attention-FFN structure, we conduct a…

We present a novel method that extends the self-attention mechanism of a vision transformer (ViT) for more accurate object detection across diverse datasets. ViTs show strong capability for image understanding tasks such as object…

The quadratic cost of self-attention in Vision Transformers (ViTs) constitutes a fundamental bottleneck for practical deployment, motivating a vibrant line of research on token reduction. Among existing approaches, token merging (ToMe) has…