Related papers: Memory Efficient Matting with Adaptive Token Routi…

The encoding of the target in object tracking moves from the coarse bounding-box to fine-grained segmentation map recently. Revisiting de facto real-time approaches that are capable of predicting mask during tracking, we observed that they…

As wireless communication systems evolve, automatic modulation recognition (AMR) plays a key role in improving spectrum efficiency, especially in cognitive radio systems. Traditional AMR methods face challenges in complex, noisy…

The quadratic complexity of self-attention mechanism presents a significant impediment to applying Transformer models to long sequences. This work explores computational principles derived from astrocytes-glial cells critical for biological…

In this paper we propose augmenting Vision Transformer models with learnable memory tokens. Our approach allows the model to adapt to new tasks, using few parameters, while optionally preserving its capabilities on previously learned tasks.…

Access to external knowledge is essential for many natural language processing tasks, such as question answering and dialogue. Existing methods often rely on a parametric model that stores knowledge in its parameters, or use a…

We present TALE, a novel training-free framework harnessing the generative capabilities of text-to-image diffusion models to address the cross-domain image composition task that focuses on flawlessly incorporating user-specified objects…

Recently, Transformers have gained significant popularity in image restoration tasks such as image super-resolution and denoising, owing to their superior performance. However, balancing performance and computational burden remains a…

Vision Transformer (ViT) architectures are becoming increasingly popular and widely employed to tackle computer vision applications. Their main feature is the capacity to extract global information through the self-attention mechanism,…

Template-matching methods for visual tracking have gained popularity recently due to their comparable performance and fast speed. However, they lack effective ways to adapt to changes in the target object's appearance, making their tracking…

Although numerous solutions have been proposed for image super-resolution, they are usually incompatible with low-power devices with many computational and memory constraints. In this paper, we address this problem by proposing a simple yet…

In this paper, we propose Mixture of Layer-Wise Tokens (MoLT), a parameter- and memory-efficient adaptation framework for audio-visual learning. The key idea of MoLT is to replace conventional, computationally heavy sequential adaptation at…

Latent Diffusion Models (LDMs) are generally trained at fixed resolutions, limiting their capability when scaling up to high-resolution images. While training-based approaches address this limitation by training on high-resolution datasets,…

The quadratic complexity of self-attention limits the scalability of transformers on long sequences. We introduce Fast Low-rank Attention Routing Engine (FLARE), a token-mixing operator that realizes low-rank attention by routing…

Recurrent-attention hybrids aim to combine the efficiency of recurrence with the expressivity of attention, but existing approaches typically apply attention uniformly across all positions, even when the recurrent state alone is sufficient…

Attention-based models, exemplified by the Transformer, can effectively model long range dependency, but suffer from the quadratic complexity of self-attention operation, making them difficult to be adopted for high-resolution image…

When arranged in a crossbar configuration, resistive memory devices can be used to execute Matrix-Vector Multiplications (MVMs), the most dominant operation of many Machine Learning (ML) algorithms, in constant time complexity. Nonetheless,…

High-resolution sensors are critical for robust autonomous perception but impose a severe memory wall on battery-constrained electric vehicles. In these systems, data movement energy often outweighs computation. Traditional image…

This paper presents an automatic network adaptation method that finds a ConvNet structure well-suited to a given target task, e.g., image classification, for efficiency as well as accuracy in transfer learning. We call the concept…

Large Reasoning Models (LRMs) have shown promising accuracy improvements on complex problem-solving tasks. While these models have attained high accuracy by leveraging additional computation at test time, they need to generate long…

We propose EMMA, an efficient and unified architecture for multimodal understanding, generation and editing. Specifically, EMMA primarily consists of 1) An efficient autoencoder with a 32x compression ratio, which significantly reduces the…