Related papers: When Quantization Is Free: An int4 KV Cache That O…

Quantization is a proven effective method for compressing large language models. Although popular techniques like W8A8 and W4A16 effectively maintain model performance, they often fail to concurrently speed up the prefill and decoding…

As large language models become increasingly prevalent, memory bandwidth constraints significantly limit inference throughput, motivating post-training quantization (PTQ). In this paper, we propose FireQ, a co-designed PTQ framework and an…

We present a 1D repetition code based on the so-called cat qubits as a viable approach toward hardware-efficient universal and fault-tolerant quantum computation. The cat qubits that are stabilized by a two-photon driven-dissipative…

Federated learning (FL) is a decentralized approach, enabling multiple participants to collaboratively train a model while ensuring the protection of data privacy. The transmission of updates from numerous edge clusters to the server…

Lossy image compression is essential for efficient transmission and storage. Traditional compression methods mainly rely on discrete cosine transform (DCT) or singular value decomposition (SVD), both of which represent image data in…

Key-value (KV) caching has become the de-facto to accelerate generation speed for large language models (LLMs) inference. However, the growing cache demand with increasing sequence length has transformed LLM inference to be a memory bound…

This study proposes a Quantum Fourier Transform (QFT)-enhanced quantum kernel for short-term time-series forecasting. Each signal is windowed, amplitude-encoded, transformed by a QFT, then passed through a protective rotation layer to avoid…

Recently, quantization has been widely used for the compression and acceleration of large language models (LLMs). Due to the outliers in LLMs, it is crucial to flatten weights and activations to minimize quantization error with equally…

Many computational factors limit broader deployment of large language models. In this paper, we focus on a memory bottleneck imposed by the key-value (KV) cache, a computational shortcut that requires storing previous KV pairs during…

Continuous-variable quantum key distribution (CV-QKD) has been proposed as a method for securely exchanging keys to protect against the security concerns caused by potential advancements in quantum computing. In addition to optical fibre…

Federated fine-tuning provides a practical route to adapt large language models (LLMs) on edge devices without centralizing private data, yet in mobile deployments the training wall-clock is often bottlenecked by straggler-limited uplink…

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…

Compressing large language models (LLMs) for deployment on commodity GPUs remains challenging: conventional scalar quantization is limited to fixed bit-widths (e.g., 8/4/3-bit), offers only a few discrete compression points, and typically…

Practical realizations of quantum repeaters require quantum memory simultaneously providing high retrieval efficiency, long lifetime and multimode storages. So far, the combination of high retrieval efficiency and spatially multiplexed…

Quantum memory for flying optical qubits is a key enabler for a wide range of applications in quantum information science and technology. A critical figure of merit is the overall storage-and-retrieval efficiency. So far, despite the recent…

While LLMs are powerful embedding backbones, their application in training-free settings faces two structural challenges: causal attention restricts early tokens from accessing subsequent context, and the next-token prediction objective…

Large Language Models (LLMs) have demonstrated remarkable proficiency across a wide range of tasks. However, LLMs often require larger batch sizes to enhance throughput or longer context lengths to meet task demands, which significantly…

The growing adoption of Apple Silicon for machine learning development has created demand for efficient inference solutions that leverage its unique unified memory architecture. However, existing tools either lack native optimization…

Quantum computing is in an era of limited resources. Current hardware lacks high fidelity gates, long coherence times, and the number of computational units required to perform meaningful computation. Contemporary quantum devices typically…

Video vision-language models (VLMs) keep paying for visual state the stream already told us was stable. The factory wall did not move, but most VLM pipelines still hand the model dense RGB frames or a fresh prefix again. We study that waste…