Related papers: SSD: Spatial-Semantic Head Decoupling for Efficien…

Recent work on KV cache quantization, culminating in TurboQuant, has approached the Shannon entropy limit for per-vector compression of transformer key-value caches. We observe that this limit applies to a strictly weaker problem than the…

Autonomous vehicles increasingly rely on cameras to provide the input for perception and scene understanding and the ability of these models to classify their environment and objects, under adverse conditions and image noise is crucial.…

Large language models (LLMs) excel at processing long sequences, boosting demand for key-value (KV) caching. While recent efforts to evict KV cache have alleviated the inference burden, they often fail to allocate resources rationally…

As context windows in LLMs scale to 100K+ tokens, the key-value (KV) cache becomes the dominant memory bottleneck, with recent methods claiming 80-90% savings and minimal benchmark degradation. We argue these evaluations miss a structural…

Key-Value cache (\texttt{KV} \texttt{cache}) compression has emerged as a promising technique to optimize Large Language Model (LLM) serving. It primarily decreases the memory consumption of \texttt{KV} \texttt{cache} to reduce the…

Large language models (LLMs) can now handle longer sequences of tokens, enabling complex tasks like book understanding and generating lengthy novels. However, the key-value (KV) cache required for LLMs consumes substantial memory as context…

Visual Autoregressive(VAR) models enhance generation quality but face a critical efficiency bottleneck in later stages. In this paper, we present a novel optimization framework for VAR models that fundamentally differs from prior approaches…

Recent advances in generative compression methods have demonstrated remarkable progress in enhancing the perceptual quality of compressed data, especially in scenarios with low bitrates. However, their efficacy and applicability to achieve…

Withtherapid advancement of large language models (LLMs), the context length for inference has been continuously increasing, leading to an exponential growth in the demand for Key-Value (KV) caching. This has resulted in a significant…

In deep CNN based models for semantic segmentation, high accuracy relies on rich spatial context (large receptive fields) and fine spatial details (high resolution), both of which incur high computational costs. In this paper, we propose a…

Transformer-based Large Language Models rely critically on the KV cache to efficiently handle extended contexts during the decode phase. Yet, the size of the KV cache grows proportionally with the input length, burdening both memory…

The Dynamic Vision Sensor (DVS) is an innovative technology that efficiently captures and encodes visual information in an event-driven manner. By combining it with event-driven neuromorphic processing, the sparsity in DVS camera output can…

Huge memory consumption has been a major bottleneck for deploying high-throughput large language models in real-world applications. In addition to the large number of parameters, the key-value (KV) cache for the attention mechanism in the…

Convolutional neural networks (CNNs) are highly successful for super-resolution (SR) but often require sophisticated architectures with heavy memory cost and computational overhead, significantly restricts their practical deployments on…

Camera-based 3D semantic scene completion (SSC) plays a crucial role in autonomous driving, enabling voxelized 3D scene understanding for effective scene perception and decision-making. Existing SSC methods have shown efficacy in improving…

Feed-forward 3D foundation models face a key challenge: the quadratic computational cost introduced by global attention, which severely limits scalability as input length increases. Concurrent acceleration methods, such as token merging,…

Large language models (LLMs) have gained great success in various domains. Existing systems cache Key and Value within the attention block to avoid redundant computations. However, the size of key-value cache (KV cache) is unpredictable and…

Semantic communication has drawn substantial attention as a promising paradigm to achieve effective and intelligent communications. However, efficient image semantic communication encounters challenges with a lower testing compression ratio…

Given the quadratic complexity of attention, KV cache eviction is vital to accelerate model inference. Current KV cache eviction methods typically rely on instantaneous heuristic metrics, implicitly assuming that score magnitudes are…

Large language models (LLMs) have demonstrated remarkable performance, but their long-context reasoning remains constrained by the excessive memory required for the Key-Value (KV) cache. This makes KV cache compression a critical step…