相关论文: VAT: Asymptotic Cost Analysis for Multi-Level Key-…

Modern multimodal large language models (MLLMs) can reason over hour-long video, yet their key-value (KV) cache grows linearly with time-quickly exceeding the fixed memory of phones, AR glasses, and edge robots. Prior compression schemes…

The KV cache in self-attention has emerged as a major bottleneck in long-context and large-batch inference for LLMs. Existing approaches often treat sparsity prediction and compression as separate modules, relying on auxiliary index…

As Large Language Models (LLMs) scale in size and context length, the memory requirements of the key value (KV) cache have emerged as a major bottleneck during autoregressive decoding. The KV cache grows with sequence length and embedding…

Remote in-memory key-value (KV) stores serve as a cornerstone for diverse modern workloads, and high-speed range scans are frequently a requirement. However, current architectures rarely achieve a simultaneous balance of peak efficiency,…

The high memory demands of the Key-Value (KV) Cache during the inference of Large Language Models (LLMs) severely restrict their deployment in resource-constrained platforms. Quantization can effectively alleviate the memory pressure caused…

Audio-visual video segmentation~(AVVS) aims to generate pixel-level maps of sound-producing objects within image frames and ensure the maps faithfully adhere to the given audio, such as identifying and segmenting a singing person in a…

Vision Transformers (ViTs) have recently garnered considerable attention, emerging as a promising alternative to convolutional neural networks (CNNs) in several vision-related applications. However, their large model sizes and high…

We observe two major trends in LLM-based generative AI: (1) inference is becoming the dominant factor in terms of cost and power consumption, surpassing training, and (2) retrieval augmented generation (RAG) is becoming prevalent. When…

The steady progress of quantum hardware is motivating the search for novel quantum algorithm optimization strategies for near-term, real-world applications. In this study, we propose a novel feature map optimization strategy for Quantum…

A cross-benchmark has been done on three critical aspects, data imputing, feature selection and regression algorithms, for machine learning based chemical vapor deposition (CVD) virtual metrology (VM). The result reveals that linear feature…

Recently, video language models (VLMs) have been applied in various fields. However, the visual token sequence of the VLM is too long, which may cause intolerant inference latency and GPU memory usage. Existing methods propose…

Model quantization has become a crucial technique to address the issues of large memory consumption and long inference times associated with LLMs. Mixed-precision quantization, which distinguishes between important and unimportant…

With the rise of Deep Neural Networks, machine learning systems are nowadays ubiquitous in a number of real-world applications, which bears the need for highly reliable models. This requires a thorough look not only at the accuracy of such…

Large Language Models (LLMs) suffer inference-time memory bottlenecks dominated by the attention Key-Value (KV) cache, which scales with model size and context length. While KV-cache quantization alleviates this cost, bit allocation between…

Specialized Deep Learning (DL) acceleration stacks, designed for a specific set of frameworks, model architectures, operators, and data types, offer the allure of high performance while sacrificing flexibility. Changes in algorithms,…

We study a crucial yet often overlooked issue inherent to Vision Transformers (ViTs): feature maps of these models exhibit grid-like artifacts, which hurt the performance of ViTs in downstream dense prediction tasks such as semantic…

Multiple-view visualization (MV) is a layout design technique often employed to help users see a large number of data attributes and values in a single cohesive representation. Because of its generalizability, the MV design has been widely…

Variational Quantum Algorithms (VQAs) combine quantum circuits with classical optimization to tackle problems that may benefit from the capabilities of near-term quantum hardware. In knowledge graph embedding, recent proposals based on this…

Quantum Support Vector Machines face scalability challenges due to high-dimensional quantum states and hardware limitations. We propose an embedding-aware quantum-classical pipeline combining class-balanced k-means distillation with…

Large models based on the Transformer architecture are susceptible to extreme-token phenomena, such as attention sinks and value-state drains. These issues, which degrade model performance, quantization fidelity, and interpretability, arise…