Knowledge catalogue
Integrate NVIDIA Resiliency Extension (NVRx) into PyTorch FSDP training on Amazon EKS to overlap checkpoint I/O with training and recover from GPU faults in seconds. This post covers async checkpointi
arXiv:2609.17391v1 Announce Type: new Abstract: Model serving is one of the largest cost drivers in production recommender systems. Maximizing its throughput requires navigating a deeply layered hiera
arXiv:2609.16500v1 Announce Type: new Abstract: Hidden Semi-Markov Models (HSMMs) are fundamental probabilistic models widely adopted across diverse domains, from computational biology to finance and
Agentic AI workflows using NVIDIA Omniverse libraries automate preparation of Blender scenes for robotics simulation by adding semantic labels, sensor definitions, physics properties and validating th
arXiv:2609.16085v1 Announce Type: cross Abstract: Eight-bit integer (INT8) post-training quantization is the default recipe for edge deployment, under a widely held assumption: INT8 makes inference fa
System performance, efficient infrastructure scaling and continuous software optimization are key levers that determine AI inference economics. Higher system performance means more tokens generated, r
The Information: Sources: Apple is developing enterprise AI servers powered by two or four M8 Ultra chips, set for 2029, and is considering integrating Nvidia's NVLink Fusion — Apple has been working
Cristina Criddle / Financial Times: Sources: OpenAI and Anthropic staff felt blindsided by Dario Amodei's and Sam Altman's calls to slow the frontier; some fear evaluators may compromise security — St
cuTile Rust extends Rust’s ownership model to tile‑based GPU kernels by splitting mutable outputs into disjoint parts while preserving host‑side ownership across launches. An agent skill translates cu
Air pollution is a serious public health risk, contributing to an estimated 30,000 deaths in the U.K. alone last year. Data-driven insights can help — but computing air quality with traditional chemis
arXiv:2609.14105v1 Announce Type: new Abstract: Heat Kernel Textures (HKTex) represent surface appearance with intrinsic anisotropic kernels, but evaluate them using 50 global Laplace-Beltrami eigende
arXiv:2609.13846v1 Announce Type: cross Abstract: Delayed Tensor Parallelism (DTP) removes the blocking all-reduce of tensor-parallel Transformer inference. Every device adds its own partial output to
AI Engineer Paris is one week away! A huge thank you to all our incredible sponsors for making this special event possible: @nvidia @FactoryAI @sentry @CockroachDB @SonarSource @NotionHQ @SierraPlatfo
Ian Buck, vice president of hyperscale and high-performance computing at NVIDIA, Tuesday spoke on AI factory efficiency at the AI Infra Summit, the Santa Clara Convention Center event that has morphed
If a measure of one firm’s impact is based on the company it keeps, then Salesforce Inc. has made a significant leap into the artificial intelligence conversation for 2026. At Dreamforce, the customer
arXiv:2609.13592v1 Announce Type: cross Abstract: GPU memory bandwidth and capacity limit throughput in large language model (LLM) inference. The GPU memory system consists of a primary tier of high-b
arXiv:2609.14339v1 Announce Type: new Abstract: Decentralized training enables large-model training over low-end GPUs and internet-grade connections, but communication along both data-parallel and pip
Brody Ford / Bloomberg: During a Salesforce event, Jensen Huang says the AI industry doesn't need any new laws or regulations and market forces will help companies safely innovate — Nvidia Corp. Chief
On a sweltering August evening in Silicon Valley, as the sun dropped and air conditioning loads spiked, Silicon Valley Power sent a signal to an AI factory to adjust its power consumption. Varun Sivar
arXiv:2609.15895v1 Announce Type: new Abstract: Physical AI relies on frequently-updated, latency-sensitive video stream to perceive, reason, and interact with the physical world, resulting in strict
arXiv:2609.13243v1 Announce Type: cross Abstract: We present GzDRL, a novel single-process reinforcement learning (RL) framework for Gazebo that overcomes longstanding bottlenecks in scalable, reprodu
The NVIDIA Vera Rubin platform attains superior performance‑per‑watt by combining factory‑level DSX MaxLPS power shifting, rack‑level capacitors with Intelligent Power Smoothing, and the Groq 3 LPX de
NVIDIA NVLink 6 offers a natively lossless fabric for large‑scale AI factories by integrating lightweight Forward Error Correction, physical‑layer retries, UPHY recovery and credit‑based flow control
arXiv:2601.14172v4 Announce Type: replace-cross Abstract: We study neural multi-label classification under severe label imbalance through sentence-level detection of the 19 refined Schwartz human valu
arXiv:2505.12384v2 Announce Type: replace Abstract: Semantic SLAM holds promise for robust robot navigation in complex environments, but its practicality on embedded systems remains uncertain. This pa
Jensen Huang completely destroys Jacob Coxon’s (ex-Anthrpic employee) 10% extinction prediction. no data, no scientific grounding, no defensible 10%. 'First of all, we shouldn’t [try to explain a 10%
arXiv:2609.15863v1 Announce Type: new Abstract: Video diffusion models are stochastic and hard to control: precise content often requires repeated sampling without guaranteed success, and long-horizon
arXiv:2609.15647v1 Announce Type: new Abstract: Medical counterfactual generation modifies images to change model predictions for interpretability. However, existing diffusion-based approaches are oft
arXiv:2609.13585v1 Announce Type: cross Abstract: Communication has become a bottleneck in distributed training and inference of large models. Overlapping communication with computation at the granula
Kai Nicol-Schwarz / CNBC: Netherlands-based inference chip startup Euclyd raised a €200M+ Series A co-led by Samsung, Somerset Capital, Scaleup Europe Fund, and Innovation Industries — Samsung has bac
arXiv:2609.14237v1 Announce Type: cross Abstract: LLM serving systems increasingly disaggregate inference into finer-grained stages, with recent approaches separating attention from FFN or MoE executi
arXiv:2609.14213v1 Announce Type: cross Abstract: Modern mobile inference runs on heterogeneous platforms combining mobile GPUs with multiple CPU core clusters. Existing optimizations typically exploi
arXiv:2609.14856v1 Announce Type: cross Abstract: Semantic watermarks for diffusion models embed ownership information into the generative process while preserving perceptual quality, but Gaussian-Sha
NVIDIA FLARE separates persistent federation services from dynamically launched job workers, allowing each participating site to deploy federated learning jobs on Docker, Kubernetes, or Slurm without
arXiv:2609.13551v1 Announce Type: new Abstract: Static-image benchmarks do not capture the computational and temporal requirements of practical orchard video analytics. This study presents an end-to-e
arXiv:2609.14991v1 Announce Type: new Abstract: Open Thai automatic speech recognition (ASR) is dominated by offline, Whisper-based models that read the whole utterance before transcribing, ruling out
arXiv:2609.15810v1 Announce Type: new Abstract: Diffusion Transformers deliver state-of-the-art video generation, but their long spatiotemporal sequences make attention the dominant deployment cost, a
LM Studio’s Voice Transcription now supports Apple‑Silicon Macs and PCs with NVIDIA GPUs, with AMD GPU support slated for a future release. The announcement accompanies the Bionic 1.1.3 version, relea
Well.. @levie and I filmed this episode of Training Data a week or two ago, when the “current thing” was Doug Leone’s novacaine root canals instead of pacing the frontier… Simpler times! But Aaron’s a
arXiv:2609.14146v1 Announce Type: cross Abstract: Vision-language-action (VLA) deployment can reduce inference latency while changing closed-loop task behavior. We evaluate HuggingFaceVLA/smolvla_libe
arXiv:2609.15130v1 Announce Type: cross Abstract: woma is a real-time foundation model for gastrointestinal endoscopy: a network trained without labels on about a million endoscopy frames, from which
arXiv:2609.12471v1 Announce Type: new Abstract: We introduce AMDKernelVault, an open HIP and Triton kernel corpus and training framework for recent AMD CDNA GPUs. Existing LLM-based kernel agents are
arXiv:2609.12218v1 Announce Type: cross Abstract: The growing use of electroencephalography (EEG) motivates automated analysis that is accurate, transferable, and deployable on constrained hardware. R
arXiv:2609.12923v1 Announce Type: cross Abstract: A single SM utilization percentage can make an LLM inference workload look compute-saturated while hiding how much useful work is being done. The prob
arXiv:2609.13010v1 Announce Type: new Abstract: Optimal transport (OT) compares distributions and aligns datasets in machine learning, yet unregularized discrete OT requires a linear program with quad
arXiv:2511.15015v4 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) has become a practical architecture for scaling LLM capacity while keeping per-token compute modest, but deploying Mo
arXiv:2609.12412v1 Announce Type: cross Abstract: Foundation models, including large language models, vision-language models, and time-series foundation models, are increasingly deployed on embedded a
Hi, For single-GPU training, I’m using Hugging Face SFTTrainer with auto_find_batch_size=True, which automatically reduces the batch size after a CUDA OOM until it finds a batch size that works. I wou
My prompt is: Epic high-fantasy concept art, ultra-detailed. A road crossing golden plains leading toward a colossal dwarven mountain hall entrance recessed into themouth of a giant cave. The whole en
Nvidia CEO Jensen Huang took a call from President Trump on Monday while onstage at the All-In Podcast's All-In Summit. It's not the first time Huang has taken a call from the president during work, b
SAN FRANCISCO, CA, September 14, 2026 — Lambda, Inc. (“Lambda”), the Superintelligence Cloud, today announced it has signed the White House Ratepayer Protection Pledge, affirming its commitment to ens
maybe aidan was right and other companies are also starting to realize this, ZDR means nothing SITUATION DETECTED: Nvidia, Palantir, and Booz Allen Hamilton are restricting or eliminating the use of A
MUST SEE: Amazing moment as President Trump calls Nvidia CEO Jensen Huang while he's on stage at the All-In Summit. @POTUS on AI Doomerism: “I'm telling you, it's all a hoax… and we're not going to le
Shubhangi Goel / Business Insider: Nuance Labs, which builds low-latency AI avatars that can have face-to-face conversations, raised a 50M Series A led by Lightspeed, with Nvidia participating — A sta
The Information: Nvidia and Booz Allen Hamilton limit Fable use as Anthropic doesn't guarantee zero data retention; source: Palantir hasn't made Fable available via its software — As paranoia rises ov
Nvidia Corp. said today it’s tackling one of the major headaches for developers of quantum applications with the launch of a new orchestration layer within its open-source CUDA-Q platform. The announc
okay wow. per folks there, Trump called Jensen huang in the middle of his interview and jensen put the phone on speakerphone Jensen thanked trump for his social media post this morning pouring cold wa
arXiv:2609.11956v1 Announce Type: new Abstract: Post-training with reinforcement learning (RL) is a critical phase in the development of code-generating large language models (LLMs), as it ensures adh
arXiv:2609.12900v1 Announce Type: cross Abstract: Transient glacier simulations with higher-order ice flow require the repeated solution of a nonlinear problem as the geometry evolves. In the online m
Reasoning from scratch round 3: This time, I cover generating a verifier for... a) ...evaluation (base model versus any future model improvement) b) ...the reinforcement learning with verifiable rewar