Knowledge catalogue
Hartley Charlton / MacRumors: Apple unveils the 2nm A20 Pro, featuring a 6-core CPU with two “desktop class” super cores, a 7-core GPU up to 40% faster, and 32 Neural Engine cores in total — Apple tod
arXiv:2609.07094v1 Announce Type: new Abstract: Reasoning is a promising route to the generalization that autonomous driving requires in the long tail, as it can infer how the elements of a scene depe
CUDA Toolkit 13.4 introduces Windows‑on‑Arm support and preview functional compatibility for the NVIDIA Rubin architecture (compute capability 107), enabling cross‑platform CUDA development on ARM sys
arXiv:2609.07264v1 Announce Type: new Abstract: Inference energy per token drives the cost and carbon footprint of deployed transformers. It is dominated by dense matrix products that incur fused mult
arXiv:2609.06551v1 Announce Type: cross Abstract: Mobile vendors and application developers increasingly deploy LLMs on smartphones for diverse prefill-only services. Yet current systems rely mainly o
The Compute Exchange Inc., a startup that matches buyers and sellers of graphics processing units, is launching a GPU inventory management capability intended to give enterprise buyers a consolidated
arXiv:2609.06046v1 Announce Type: cross Abstract: We present a modular, high-fidelity simulation framework for the development and benchmarking of flight control strategies in fixed-wing aerial robots
arXiv:2609.08136v1 Announce Type: new Abstract: This paper introduces rlaopt, a PyTorch-based package for large-scale optimization and scientific computing using randomized numerical linear algebra (R
arXiv:2609.08722v1 Announce Type: cross Abstract: Pigment deposition in paper marbling displaces the pattern already present, coupling the appearance of each gesture to later actions. We recover execu
It's crazy how far small models can be pushed. Robbyant just open-sourced LingBot-World 2.0 Small, a 1.3B world model that generates an interactive world in real time on a single consumer GPU. Same pa
arXiv:2609.07816v1 Announce Type: new Abstract: Linear attention is increasingly used in frontier language models for efficient long-context inference and constant-memory decoding. Its fixed-size recu
Lightbits Labs Ltd. today announced the general availability of Inferra, a software engine designed to improve the economics and performance of artificial intelligence inference by moving key-value ca
arXiv:2609.08010v1 Announce Type: new Abstract: This paper presents a general framework for simulating multi-body space robots with contact. We bring efficient, large-scale robot simulation to in-spac
arXiv:2609.05807v1 Announce Type: new Abstract: Optical Chemical Structure Recognition (OCSR) is a fundamental component of chemical literature mining, enabling molecular database construction, reacti
arXiv:2602.10114v2 Announce Type: replace Abstract: Centralized motion planning algorithms struggle to scale in multi-arm manipulation, where inter-arm coupling and tight workspaces amplify complexity
At the IBC conference, running Sept. 11-14 in Amsterdam, the creative, technology and business communities are coming together to turn ideas into action and discuss innovations across the media and en
arXiv:2609.06810v1 Announce Type: new Abstract: Optical coherence tomography (OCT) offers compact, contactless, micron-scale imaging suitable for intraoperative guidance, but native OCT volumes are di
arXiv:2609.08800v1 Announce Type: cross Abstract: Three properties determine whether a differentiable simulator can drive gradient-based optimization through contact: simulation accuracy, gradient rel
arXiv:2609.09059v1 Announce Type: new Abstract: While many video-game environments (VGEs) have played crucial roles in advancing reinforcement learning (RL), developing novel VGEs or modifying existin
arXiv:2405.18253v4 Announce Type: replace Abstract: Data plays a central role in advancements in modern artificial intelligence, with high-quality data emerging as a key driver of model performance. T
“real science is not a clout chase on social media or a compute spike spent to rob the clay mathematics institute it is a quest for elegance physical truth and universal rigor to decode reality true a
arXiv:2609.06712v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) achieve strong video generation quality, but their dense spatiotemporal self-attention scales quadratically with sequence
TorchServe is no longer maintained, leaving teams to own the entire GPU inference stack. The AWS Ray Serve Deep Learning Container is a supported, pre-tested container with the framework, GPU drivers,
arXiv:2609.06144v1 Announce Type: new Abstract: Visual dubbing must synchronize mouth motion with replacement speech while preserving identity, appearance, and temporal consistency. Although X-Dub pro
arXiv:2609.07843v1 Announce Type: cross Abstract: Machine learning has shown its largest gains in the band below 10 ms inside a 3GPP new radio (NR) 5G distributed unit (DU): link adaptation, per-slot
Encode‑Prefill‑Decode (EPD) disaggregation is an inference optimization in NVIDIA Dynamo that separates vision encoding from LLM prefill–decode stages for multimodal requests. On image‑heavy prompts,
Most of the new ~30B (and now ~10B, thankfully for my GPU) models we see score really high on benchmarks, but I feel like they don't push back on dumb ideas enough. I think most people don't being lik
David Hölz tweets that he would like cloud‐based AI platforms to offer easier, paid options for deploying high‑performance virtual machines—specifically servers with many CPU cores or dedicated GPU r
NVIDIA introduced two Rust projects for GPU development in September 2026: `cuda‑oxide`, a nightly‑only backend that compiles SIMT‑style kernels to PTX via LLVM and uses DisjointSlice and launch contr
Led by @Samsung, co-led by @eqt's Scaleup Europe Fund and @PSG_equity, with continued backing from @ASMLcompany, @nvidia, @BNPParibas CIB and others. This fuels our infrastructure and product capabili
Ari Levy / CNBC: Qualcomm signs a deal with Amazon to provide “multiple generations of customized silicon” to help build AWS' AI infrastructure for inference; QCOM jumps ~5% — Qualcomm shares rose 4%
SF Tech Week meets Fleet Week ✈️ Oct 9: Together AI, @dtcp_capital, and @nvidia are taking over a private waterfront chalet for a front row seat to the Blue Angels. Custom aviators. Great food and dri
arXiv:2609.04557v1 Announce Type: cross Abstract: Quantum error-correction decoders are typically benchmarked against synthetic circuit-level noise, under the assumption that a decoder's ranking under
arXiv:2609.04971v1 Announce Type: cross Abstract: Large Reasoning Models (LRMs) achieve superior problem-solving through extended Chain-of-Thought (CoT) generation, but the resulting key-value (KV) ca
arXiv:2609.04999v1 Announce Type: new Abstract: This paper describes the participation of the BIT.UA team from the University of Aveiro in the 14th edition of the BioASQ Task B challenge on biomedical
arXiv:2609.04895v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models activate only a small subset of experts per token, but the full expert set often exceeds GPU memory, causing repeated we
arXiv:2609.05255v1 Announce Type: new Abstract: Explicit primitive-based radiance fields such as 3D Gaussian Splatting typically model view-dependent appearance using low-order spherical harmonics (SH
arXiv:2609.04266v1 Announce Type: cross Abstract: Softmax is a key operation in Transformer attention, but its exponentiation and normalization add significant overhead in compute-in-memory (CIM) acce
arXiv:2609.04910v1 Announce Type: new Abstract: Gaussian kernel sums are the computational core of maximum mean discrepancies (MMDs), kernel gradient flows, Stein variational gradient descent (SVGD),
arXiv:2609.05138v1 Announce Type: new Abstract: Comparisons between GPU implementations are usually asymmetric: one side is tuned by its author, the other is run as found. I report a programme that tu
arXiv:2609.04222v1 Announce Type: cross Abstract: We present GEPARD (Generative, Prosody-aware, Autoregressive text-to-speech model for Realtime Dialogue), a streaming text-to-speech model for real-ti
arXiv:2502.21318v4 Announce Type: replace Abstract: Recent text-to-image (T2I) generation models have achieved remarkable sucess by training on billion-scale datasets, following a `bigger is better' p
I ran a 112-case MiniMax H3 quality sweep on an RTX 3090 last night trying to find the best combos . Kept the prompt, seed, reference image, RefMods, Sage setup, sampler, and scheduler stayed constant
I’ve been overwhelmed and humbled by the fact that 99% of the reactions to our intent to join forces have been positive. ❤️ Prominent tech figures, including some you could see as having a competitive
Hi, I use hermes as a harness, and I am pleased with it, but sometimes Hermes's context size is a bit too much for my system, so I wanted to delegate or straight up use a lighter option for coding tas
arXiv:2609.04262v1 Announce Type: cross Abstract: Spell correction for Japanese search queries presents unique challenges due to the co-existence of four writing scripts (Latin/romaji, hiragana, katak
arXiv:2404.07124v2 Announce Type: replace-cross Abstract: This paper presents a pipeline designed to bring ultrasound (US) plane pose estimation closer to clinical use, demonstrating the feasibility o
Ouch: “Nvidia is building the most concentrated bet on a single technology cycle that any company has ever made. If these valuations keep climbing, Jensen looks like a genius. If they don't, Nvidia is
arXiv:2609.05262v1 Announce Type: new Abstract: Computational phylogenetics has become an essential tool in historical linguistics, yet its application at a global scale remains constrained by two fac
⚠️ The most important question hardly anyone is asking is whether Jensen meant 100K+ GPUs, or 100k+ NVLink72 server racks (which contain 72 Blackwell GPUs). ⚠️ From his wording, it sure looks like the
Google has begun allowing third‑party customers to acquire or rent its TPU chips—starting with the TPUv7 “Ironwood” generation. In comparative tests against NVIDIA Volta (B200/B300), Ironwood shows up
arXiv:2609.04417v1 Announce Type: cross Abstract: Distributed AI training involves recurring rounds of data exchange between multiple pairs of GPU nodes. Slowdown in even one flow due to congestion ca
We are excited to bring the first open benchmarking of Google's TPUs to the world Running every day, on many models + scenarios $/token is better than B200 and B300 Huge shout-out to Google @inferact
New York Times: How Inspur, a blacklisted China-owned company, is bypassing US export restrictions on advanced AI chips via a network of new subsidiaries and partners — Washington imposed sanctions on
Reasoning from scratch round 2: In this video, I cover the text generation process in LLMs and KV caching (to prepare the base model before adding reasoning techniques in the upcoming ones). 00:00 Int
Sad to see Jensen claim that AGI has arrived, with no evidence and no definitions. I would urge him to read http://agidefinition.AI by @hendrycks, @Yoshua_Bengio & many others (including myself), and
Chamath says Nvidia's Hugging Face acquisition is as a massive move against AI becoming a closed source oligopoly 'Jensen and I were texting this morning. I said to him, this is the most incredible th
SemiAnalysis reported on April 17, 2024 that they had tested Anthropic’s Fable 5.1 alongside OpenAI’s Astra language models. According to their review, the comparison revealed a decisive advantage for
Wall Street Journal: A profile of Hugging Face, which started in 2016 to build a sassy chatbot for teens; CEO Clément Delangue says he approached Nvidia this summer to pursue a deal — The startup bega
This research details an agentic framework that automatically generates custom GPU kernels and rigorously validates them. By integrating automated synthesis and thorough performance testing, the syste