相关论文: IVF-TQ: Calibration-Free Streaming Vector Search v…

Product Quantization (PQ) construction is deeply integrated into vector index construction for Approximate Nearest Neighbor Search (ANNS). The rapid growth in vector dimensionality and volume has significantly increased the computational…

Vector Quantized Variational Autoencoders (VQ-VAEs) leverage self-supervised learning through reconstruction tasks to represent continuous vectors using the closest vectors in a codebook. However, issues such as codebook collapse persist in…

The Key-Value (KV) cache of Large Language Models (LLMs) is prefix-based, making it highly inefficient for processing contexts retrieved in arbitrary order. Position-Independent Caching (PIC) has been proposed to enable KV reuse without…

The default quantisation algorithms in the state-of-the-art High Efficiency Video Coding (HEVC) standard, namely Uniform Reconstruction Quantisation (URQ) and Rate-Distortion Optimised Quantisation (RDOQ), do not take into account the…

Modern LLM applications such as deep-research assistants, coding agents, and Retrieval-Augmented Generation (RAG) systems, repeatedly process long prompt histories containing shared document or code chunks, creating significant pressure on…

The Key-Value (KV) cache is central to the efficiency of transformer-based large language models (LLMs), storing previously computed vectors to accelerate inference. Yet, as sequence length and batch size grow, the cache becomes a major…

Vision transformers (ViTs) have gained popularity recently. Even without customized image operators such as convolutions, ViTs can yield competitive performance when properly trained on massive data. However, the computational overhead of…

Vector similarity search is a critical component of modern AI systems, but traditional CPU-based implementations face fundamental scalability bottlenecks for billion-scale corpora due to prohibitive computational overhead and memory…

Image tokenizers play a critical role in shaping the performance of subsequent generative models. Since the introduction of VQ-GAN, discrete image tokenization has undergone remarkable advancements. Improvements in architecture,…

Maximum inner product search (MIPS) over dense and sparse vectors have progressed independently in a bifurcated literature for decades; the latter is better known as top-$k$ retrieval in Information Retrieval. This duality exists because…

The increasing size of the Key-Value (KV) cache during the Large Language Models long-context inference is the main obstacle for its balance between the deployment cost and task accuracy. To reduce the KV cache size in such scenarios, most…

The large size of the KV cache has become a major bottleneck for serving LLMs with increasing context lengths. In response, many KV cache compression methods, such as token dropping and quantization, have been proposed. However, almost all…

It is customary to deploy uniform scalar quantization in the end-to-end optimized Neural image compression methods, instead of more powerful vector quantization, due to the high complexity of the latter. Lattice vector quantization (LVQ),…

Positron Emission Tomography (PET) is an important molecular imaging tool widely used in medicine. Traditional PET systems rely on complete detector rings for full angular coverage and reliable data collection. However, incomplete-ring PET…

Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI. Despite the overall superiority of the Decoder architecture, the gradually increasing Key-Value (KV) cache during…

Embedding layers are commonly used to map discrete symbols into continuous embedding vectors that reflect their semantic meanings. Despite their effectiveness, the number of parameters in an embedding layer increases linearly with the…

As Large Language Models (LLMs) scale to support context windows exceeding one million tokens, the linear growth of Key-Value (KV) cache imposes severe memory capacity and bandwidth bottlenecks, constraining the efficiency of long-context…

Quantum circuit cutting enables near-term quantum devices to execute workloads exceeding their qubit capacity by decomposing circuits into independently runnable fragments. While this extends computational reach, it creates a previously…

Product Quantization (PQ) has long been a mainstream for generating an exponentially large codebook at very low memory/time cost. Despite its success, PQ is still tricky for the decomposition of high-dimensional vector space, and the…

KV cache restoration has emerged as a dominant bottleneck in serving long-context LLM workloads, including multi-turn conversations, retrieval-augmented generation, and agentic pipelines. Existing approaches treat restoration as a…