hardware

If you're looking for a weekend project, how about training your own text-to-speech model from scratch on your own GPU, and then running it on any device's CPU? We just open-sourced the entire Pocket

arXiv:2608.22506v1 Announce Type: new Abstract: Claim-level Uncertainty Quantification (UQ) aims to mitigate the lack of reliability of Large Language Models (LLMs) by evaluating the factuality of eac

NVIDIA is bringing the next wave of RTX gaming to the Gamescom conference running this week in Cologne, Germany, with support for new games, anti-cheat technologies and increased visual quality. Elect

arXiv:2608.21764v1 Announce Type: cross Abstract: Event-based vision has emerged as a promising paradigm for energy-aware artificial intelligence (AI), offering sparse, low-latency visual signals that

arXiv:2608.21806v1 Announce Type: cross Abstract: Computational resources are increasingly central to NLP research, but how closely reported GPU capability aligns with scholarly impact remains unclear

The Cisco Secure AI Factory with Nvidia has been extended into the rack-scale era, offering enterprises greater full-stack operational capabilities as a result. Designed to give customers a framework

Nvidia Corp. today announced the release of Jetson Orin Nano 2, a robotics computer “brain” for running artificial intelligence and frontier-level models at the edge. In the past months, foundational

arXiv:2608.22314v1 Announce Type: new Abstract: Many image processing methods such as corner detection, optical flow and iterative enhancement make use of image tensors. Generally, these tensors are e

OpenAI Jalapeno is spicy Usually first generation chips aren't competitive, but OpenAI is beating Nvidia Blackwell and even Rubin This is huge news! We got to go into OpenAI's lab to dissect their new

OpenAI’s Jalapeño is a self‑designed ASIC for large‑language‑model inference that was taped‑out in about 16 months, developed with Broadcom and featuring HBM4 memory. Benchmarks on the InferenceX suit

arXiv:2608.23552v1 Announce Type: new Abstract: Language models are sequential processors, but long-horizon agency requires external information and computation beyond model weights and active context

Shadow Engine Recovery in NVIDIA Dynamo keeps a fully-initialized standby LLM engine on the same GPU, using the GPU Memory Service (GMS) to persist model weights and share them across engines without

Generalist AI Inc., a startup that develops artificial intelligence software for robots, has reportedly raised 200 million in funding. Axios today cited a source as saying that 8VC led the investment.

arXiv:2608.22526v1 Announce Type: new Abstract: We introduce RS^3-Prune, a training-free token-pruning recipe that instantiates as a small set of inference time hooks atop existing video object segmen

arXiv:2608.22300v1 Announce Type: new Abstract: Co-registration underlies nearly every multi-temporal and multi-sensor use of optical satellite imagery, and operational products still carry documented

Since announcing Jalapeño, our first custom inference chip, we’ve been testing it and the system around it. The results show a major advance: more intelligence from every watt and faster responses, de

arXiv:2509.04719v3 Announce Type: replace-cross Abstract: The widespread adoption of diffusion models for image generation necessitates efficient parallel inference to manage their substantial computa

arXiv:2608.21607v1 Announce Type: new Abstract: We investigate when a sparse nonnegative matrix can be recovered from a real-valued matrix of much lower rank by zeroing out its negative elements. The

arXiv:2608.22086v1 Announce Type: cross Abstract: We present SweepLSD, a line segment detector that reads the image exactly once and emits each segment within a few rows of its last pixel passing the

arXiv:2608.21555v1 Announce Type: cross Abstract: Modern machine learning compilers select tensor memory layouts to minimize execution cost under hardware constraints. Layout selection is global: an o

arXiv:2608.22007v1 Announce Type: cross Abstract: The components of a transformer communicate by writing to and reading from a shared residual stream, and mechanistic interpretability has mapped these

arXiv:2608.21887v1 Announce Type: cross Abstract: Runtime thermal management of high-performance chips depends on fast and accurate full-chip thermal maps. Conventional simulators typically estimate p

arXiv:2608.22358v1 Announce Type: new Abstract: Deep atmospheric convection governs South Asian monsoon variability, yet attempting to learn its latent world model directly from zero-inflated, heavy-t

Very interesting new work from Prime Intellect. Prime Agent is an impressive open-source self-improving harnesses. It's a harness for long-horizon agent work. A persistent IPython REPL lets the model

Vultr’s VX1™ Cloud Compute offers affordable, high‑density CPU servers tailored to the new era of agentic AI, which now demands a roughly 1:1 (or higher) CPU‑to‑GPU ratio and extensive memory manageme

arXiv:2608.22704v1 Announce Type: new Abstract: Long-form audio inputs make the KV cache the dominant memory cost of speech LLMs. Prefill-only KV compression methods permanently discard audio KV posit

AgentX 1.0 is the first fully open‑source multi‑turn agentic coding inference benchmark (Apache 2.0), released August 2026 with a 1 million‑token context and over 1 million tokens of dataset built at

arXiv:2608.21356v1 Announce Type: cross Abstract: For sixty years, machine verification has been a major cost overhead, affordable only for exceptional artifacts. Here we report that generative AI inv

arXiv:2601.12614v4 Announce Type: replace-cross Abstract: Hybrid-Vlasov simulations resolve ion-kinetic effects in the solar wind-magnetosphere interaction, but even 5D (2D + 3V) configurations are co

arXiv:2608.20725v1 Announce Type: cross Abstract: Convolution is a principal computational bottleneck in deep neural networks, and its efficiency depends on tight integration between algorithms and GP

arXiv:2608.20572v1 Announce Type: new Abstract: Convolutional Neural Networks (CNNs) face a dual challenge: vulnerability to adversarial attacks and prohibitive training cost. Adversarial training is

arXiv:2608.21174v1 Announce Type: new Abstract: Attention masks are relation-level controls: they specify which query--source pairs may interact. They do not provide a representation-carried token sta

NVIDIA’s Spectrum‑X Ethernet combines hardware‑accelerated adaptive routing, targeted congestion control and NIC‑based plane load balancing to meet the extreme bandwidth and low‑latency demands of gig

arXiv:2608.21157v1 Announce Type: cross Abstract: High-performance GPU kernels underpin modern deep learning and scientific computing. As workloads become increasingly diverse and GPU hardware evolves

NVIDIA Groq 3 LPX, when paired with the Vera Rubin NVL72 platform, delivers a record‑setting 3,431 output tokens/second on the Artificial Analysis 100K context benchmark using Gemma 4 31B, demonstrati

arXiv:2608.20350v1 Announce Type: cross Abstract: Traditional industrial agents rely on modular pipelines, including Router, Retriever, Planner, Executor, Responder, Reviewer, and other components. Th

To generate intelligence at scale, AI factories run continuously, and their economics are defined by delivered output: tokens per second, tokens per watt, cost per token, utilization and uptime. That

In the fight to defend openness in AI, the Marin project is a precious demonstration of openness in model training, with open code, data, recipes, even experimental results. Releasing AI research open

arXiv:2608.20532v1 Announce Type: new Abstract: NVIDIA provides a SASS disassembler but no public SASS assembler for recent data-center GPUs, limiting controlled machine-code rewriting. We present F2A

NVIDIA’s new Scale‑In network infrastructure, the fifth pillar of its AI networking stack, is powered by BlueField‑4 DPUs, DoCA software, and Spectrum‑X Ethernet to deliver dedicated, host‑independent

Nvidia Corp. is reportedly considering making another investment in the artificial intelligence search startup Perplexity AI Inc. A report by The Information today says the chipmaker is holding talks

Mike Wheatley / SiliconANGLE: Nvidia says its inference accelerator Groq 3 LPX has entered full production and Nebius has signed on as the first customer, and SpaceX will deploy Vera CPUs — Chipmaker

In August 2026 a senior Nvidia manager was indicted on charges linked to a Supermicro scheme that smuggled high‑end AI servers to China, breaching U.S. export controls. Taiwan’s investigation found ni

NVIDIA’s new GPUs in the Vera Rubin and Blackwell families set a new benchmark for agentic‑AI performance per watt on AgentX, an open‑source inference test that models realistic multi‑step, tool‑using

Chipmaker Nvidia Corp. says its dedicated artificial intelligence inference accelerator Groq 3 LPX has now entered full production as it strives to maintain its dominance in the world of AI compute. T

Perplexity has low tens of millions in revenue a month, and I’m not even talking about how much they lose. Nvidia had to step in to boost their valuation and give them first aid, either through cloud