相关论文: Can Cross-Layer Transcoders Replace Vision Transfo…

Vision Language Models (VLMs) have achieved remarkable success by integrating visual encoders with large language models (LLMs). While VLMs process dense image tokens across deep transformer stacks (incurring substantial computational…

Sparse autoencoders (SAEs) improve interpretability in multimodal models, but it remains unclear whether SAE features form modular, composable units for reasoning-an assumption underlying many intervention-based steering methods. We test…

The Vision Transformer (ViT) has achieved notable success in computer vision, with its variants widely validated across various downstream tasks, including semantic segmentation. However, as general-purpose visual encoders, ViT backbones…

Vision-Language Models (vLLMs) have emerged as powerful architectures for joint reasoning over visual and textual inputs, enabling breakthroughs in image captioning, cross modal retrieval, and multimodal dialogue. However, as these models…

Vision transformers (ViTs) have found only limited practical use in processing images, in spite of their state-of-the-art accuracy on certain benchmarks. The reason for their limited use include their need for larger training datasets and…

While insights into the workings of the transformer model have largely emerged by analysing their behaviour on language tasks, this work investigates the representations learnt by the Vision Transformer (ViT) encoder through the lens of…

Transformers are transforming the landscape of computer vision, especially for recognition tasks. Detection transformers are the first fully end-to-end learning systems for object detection, while vision transformers are the first fully…

Latent reasoning compresses the chain-of-thought (CoT) into continuous hidden states, yet existing methods rely on dense latent transitions that remain difficult to interpret and control. Meanwhile, sparse representation models uncover…

Transformers are very powerful tools for a variety of tasks across domains, from text generation to image captioning. However, transformers require substantial amounts of training data, which is often a challenge in biomedical settings,…

Reliable confidence estimation is critical when deploying vision models. We study error prediction: determining whether an image classifier's output is correct using only signals from a single forward pass. Motivated by internal-signal…

Implicit neural representation has recently shown a promising ability in representing images with arbitrary resolutions. In this paper, we present a Local Implicit Transformer (LIT), which integrates the attention mechanism and frequency…

Vision Transformers (ViTs) have been widely used in large-scale Vision and Language Pre-training (VLP) models. Though previous VLP works have proved the effectiveness of ViTs, they still suffer from computational efficiency brought by the…

Vision-Language-Action (VLA) models have emerged as a dominant paradigm for generalist robotic manipulation, unifying perception and control within a single end-to-end architecture. However, despite their success in controlled environments,…

Autoencoding has achieved great empirical success as a framework for learning generative models for natural images. Autoencoders often use generic deep networks as the encoder or decoder, which are difficult to interpret, and the learned…

Change detection in remote sensing images is essential for tracking environmental changes on the Earth's surface. Despite the success of vision transformers (ViTs) as backbones in numerous computer vision applications, they remain…

Vision Transformers (ViTs) have redefined image classification by leveraging self-attention to capture complex patterns and long-range dependencies between image patches. However, a key challenge for ViTs is efficiently incorporating…

Deep learning technology can be used as an assistive technology to help doctors quickly and accurately identify COVID-19 infections. Recently, Vision Transformer (ViT) has shown great potential towards image classification due to its global…

Visual transformers have achieved remarkable performance in image classification tasks, but this performance gain has come at the cost of interpretability. One of the main obstacles to the interpretation of transformers is the…

Distinguishing among different marine benthic habitat characteristics is of key importance in a wide set of seabed operations ranging from installations of oil rigs to laying networks of cables and monitoring the impact of humans on marine…

We propose a new class of linear Transformers called FourierLearner-Transformers (FLTs), which incorporate a wide range of relative positional encoding mechanisms (RPEs). These include regular RPE techniques applied for sequential data, as…