JadePuffer agentic attacks now target AI model data with ransomware

The JadePuffer autonomous AI agent has upgraded with custom malware called EncForge that focuses on encrypting AI assets, ...
SDxCentral

TurboQuant: Is compression all you need to beat the memory crunch?

Vector quantization, stock dips & RAMageddon – the real story behind how a memory compression algorithm went viral ...
GeekWire

Microsoft says its data centers use 90% less water than its earliest facilities as public concern grows

Microsoft announced Wednesday that over the past two decades, it has become dramatically more efficient in its use of water to cool data centers, slashing its consumption rate by 90% compared to ...
GitHub

EntropyKV: Value-Weighted KV Cache Eviction with Layer-Adaptive Recency Allocation

EntropyKV is an online, 100% attention-free key-value (KV) cache eviction policy designed to run long-context LLMs on consumer-grade GPUs. Traditional KV cache compression methods (e.g., H2O, SnapKV) ...
TechCrunch

Nvidia wants to cut data center water use, but that’s not the same as fixing AI’s water problem

Nvidia just announced a warm-water cooling system that it says can dramatically reduce the amount of water a data center uses — eliminating “pretty much all water usage” inside the data center, ...
IEEE

Diagnosing and Improving Vector-Quantization-Based Blind Image Restoration

Abstract: Vector-Quantization (VQ) based discrete generative models are widely used to learn powerful high-quality (HQ) priors for blind image restoration (BIR). In this paper, we diagnose the ...
IEEE

Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrieval

Abstract: Neural contextual biasing allows speech recognition models to leverage contextually relevant information, leading to improved transcription accuracy. However, the biasing mechanism is ...