Related papers: An Efficient Codebook Initialization Approach for …
Large Language Models (LLMs) are increasingly used in applications requiring long context lengths, but the key-value (KV) cache often becomes a memory bottleneck on GPUs as context grows. To address this, we propose Commutative Vector…
Continuous representation of words is a standard component in deep learning-based NLP models. However, representing a large vocabulary requires significant memory, which can cause problems, particularly on resource-constrained platforms.…
The rapid growth of visual data under stringent storage and bandwidth constraints makes extremely low-bitrate image compression increasingly important. While Vector Quantization (VQ) offers strong structural fidelity, existing methods lack…
Large Language Models (LLMs) have achieved remarkable success but face significant computational and memory challenges, particularly due to their extensive output vocabularies. The final linear projection layer, mapping hidden states to…
Approaching the 1.5329-dB shaping (granular) gain limit in mean-squared error (MSE) quantization of R^n is important in a number of problems, notably dirty-paper coding. For this purpose, we start with a binary low-density generator-matrix…
The rapid growth of the big neural network models puts forward new requirements for lightweight network representation methods. The traditional methods based on model compression have achieved great success, especially VQ technology which…
Discrete image tokenization is a key bottleneck for scalable visual generation: a tokenizer must remain compact for efficient latent-space priors while preserving semantic structure and using discrete capacity effectively. Existing…
We present an initialisation method for variational quantum algorithms applicable to intermediate scale quantum computers. The method uses simulated annealing of the efficiently simulable Clifford parameter points as a pre-optimisation to…
Recently, many deep image compression methods have been proposed and achieved remarkable performance. However, these methods are dedicated to optimizing the compression performance and speed at medium and high bitrates, while research on…
Reducing the data footprint of visual content via image compression is essential to reduce storage requirements, but also to reduce the bandwidth and latency requirements for transmission. In particular, the use of compressed images allows…
Language Models (LLMs) are often quantized to lower precision to reduce the memory cost and latency in inference. However, quantization often degrades model performance, thus fine-tuning is required for various down-stream tasks.…
Taking an image and question as the input of our method, it can output the text-based answer of the query question about the given image, so called Visual Question Answering (VQA). There are two main modules in our algorithm. Given a…
We simulate the Lipkin-Meshkov-Glick (LMG) model using the Variational-Quantum-Eigensolver (VQE) algorithm on a neutral atom quantum computer. We test the ground-state energy of spin systems with up to 15 spins. Two different encoding…
With the rapid development of Vision-Language Models (VLMs) and the growing demand for their applications, efficient compression of the image inputs has become increasingly important. Existing VLMs predominantly digest and understand…
Nowadays, the digital world is most focused on storage space and speed. With the growing demand for better bandwidth utilization, efficient image data compression techniques have emerged as an important factor for image data transmission…
Quantum circuit initialisation is a key bottleneck in variational quantum algorithms (VQAs), strongly impacting optimisation stability and convergence. Recent work shows that large language models (LLMs) can synthesise high-quality…
To improve storage and transmission, images are generally compressed. Vector quantization (VQ) is a popular compression method as it has a high compression ratio that suppresses other compression techniques. Despite this, existing…
Image compression using neural networks have reached or exceeded non-neural methods (such as JPEG, WebP, BPG). While these networks are state of the art in ratedistortion performance, computational feasibility of these models remains a…
Due to the substantial scale of Large Language Models (LLMs), the direct application of conventional compression methodologies proves impractical. The computational demands associated with even minimal gradient updates present challenges,…
Although deep learning based image compression methods have achieved promising progress these days, the performance of these methods still cannot match the latest compression standard Versatile Video Coding (VVC). Most of the recent…