Search: “nvidia”

arXiv:2609.32380v1 Announce Type: new Abstract: Data attribution methods used in practice (TRAK, LoGRA, EK-FAC) are post-hoc: after training they make a second pass over the training set to recompute

arXiv:2609.31938v1 Announce Type: new Abstract: Generative world models can provide visual rollouts for embodied planning, yet their feasibility on edge devices depends not only on the learned model b

arXiv:2609.35570v1 Announce Type: cross Abstract: Vision-language navigation (VLN) models perform well but target compute-rich platforms, limiting deployment on memory- and power-constrained robotic e

arXiv:2609.35587v1 Announce Type: new Abstract: GPU libraries such as CUTLASS expose tens of thousands of semantically equivalent kernels for a single operation, making exhaustive autotuning expensive

arXiv:2609.34702v1 Announce Type: new Abstract: Future Mars missions will require rover autonomy that can operate across unstructured terrain, changing illumination, atmospheric dust, and limited comm

arXiv:2609.31669v1 Announce Type: new Abstract: We present NanoForecast v0.5, a 6.5M-parameter forecaster that competes with models 31x its size (TimesFM, 200M parameters) after training pipeline fixe

arXiv:2609.31699v1 Announce Type: cross Abstract: A microphone on the airframe of a small multi-rotor UAV is dominated by rotor ego-noise, so spoken flight commands arrive at negative signal-to-noise

OpenAI just announced the 200 Pro plan is back but with half the total API spend included, offset by some of their smaller (NOT Astra!) getting a 50% price drop. Does this impact the average user? No.

arXiv:2609.33746v1 Announce Type: new Abstract: At each decoding step a language model attends over the key-value (KV) cache of every earlier token, so at long context the attention call is bounded by

arXiv:2609.31932v1 Announce Type: cross Abstract: Low-Earth-orbit (LEO) satellites are increasingly expected to perform onboard learning for applications such as disaster response and environmental mo

arXiv:2609.33051v1 Announce Type: new Abstract: Hybrid-attention models replace most softmax attention layers with linear attention, reducing KV-cache growth and enabling larger decode batches where r

arXiv:2609.35110v1 Announce Type: cross Abstract: Video diffusion models are rapidly scaling and exhibiting enhanced generation capabilities. Among these recent advancements, MiniMax-H3 stands out as

arXiv:2609.35493v1 Announce Type: new Abstract: Autonomous planetary exploration requires robots to navigate unknown, uneven terrain while assessing risk, traversability, and energetic cost. Quadruped

arXiv:2609.35465v1 Announce Type: new Abstract: Leech-lattice quantization gives good quality at two bits per weight, but its codebooks hold more than 10^14 points, too many for a lookup table. Our ea

arXiv:2609.35481v1 Announce Type: cross Abstract: Dynamic routing creates severe load imbalance in large-scale expert-parallel Mixture-of-Experts (MoE) training, turning GPUs that host hot experts int

arXiv:2609.30914v1 Announce Type: cross Abstract: Quantum-inspired algorithms emulate quantum mechanical principles, such as, superposition, interference, and probabilistic amplitude evolution, on cla

arXiv:2609.31551v1 Announce Type: cross Abstract: Disaggregating the two stages, Prefill and Decode, onto separate GPU pools is now a standard optimization for (text-only) LLM serving. However, multim

arXiv:2608.00008v2 Announce Type: replace Abstract: The local deployment of large language models (LLMs) is gaining traction due to privacy concerns and the desire for on-premise inference. However, t

arXiv:2609.30629v1 Announce Type: cross Abstract: Mission-critical UAVs increasingly rely on split vision-language model (VLM) perception under tight onboard-resource and wireless-communication constr

Indeed OpenAI was incompetent (and arrogant in thinking they knew it all); new cybersecurity software that they should have written themselves may help. But whether it’s enough to stop all of this rem

It's an engineering problem! This topic has gotten too political. Let's get back to the fundamentals. 'Trust and innovation are not in conflict. Safety is how trust is earned.' Today, with over 100 in

Just like you would not let a person run around your company accessing anything without any controls, you need controls and security for your digital agents. Today, with over 100 industry partners, we

arXiv:2609.31005v1 Announce Type: new Abstract: Open-vocabulary 3D maps enable robots to reason about previously unknown environments using natural language. However, existing systems typically segmen

arXiv:2609.30866v1 Announce Type: cross Abstract: In scanning microscopy, drift causes the specimen to be sampled at positions displaced from the nominal probe positions. This displacement alters the

What cracks me up is how for the last few weeks when @ZackKorman, @HeidyKhlaaf, @nathanhamiel and I (and many others) went on about how OpenAI’s cybersecurity sucked and was the key immediate problem,

Every week, I talk with founders who are building at an unbelievable pace. Teams are moving from inception to product-market fit faster than ever, with foundation models wired deeply into their core p

Hey Guys, Based on my last post on stills, I thought to experiment the same .char model with Minimax H3. I created a character model sia.char which encodes references, prompts around face, body & clot

I built MEM v3 to solve a frustrating problem in PyTorch: CUDA Out-of-Memory crashes during long training and fine-tuning runs. Instead of restarting when memory spikes or keeping batch sizes overly s

Nscale Ltd. today announced that it has secured 3.36 billion in funding to support its data center construction push. The capital will arrive in two tranches. Nscale expects to receive 2.26 billion in

you read about gpu's like the Tesla P40, V100, AMD M150 etc that people pick up for cheap. probably many others as well. Most are either server gpu's being phased out or mining discards, right? The pr

arXiv:2609.29648v1 Announce Type: new Abstract: Video object detection on edge devices runs computationally expensive detectors over long frame streams, causing high energy consumption and sustained G

musa: fix PH1 (MTT S5000) operator failures and build issues (#29193) musa: use 16-byte copies for MUSA like sm_70+ ggml_cuda_get_max_cpy_bytes() derives the copy width from CUDA_ARCH. mcc never defin

arXiv:2609.29044v1 Announce Type: cross Abstract: Pilot-aided channel estimation is a decisive block in orthogonal frequency-division multiplexing (OFDM) receivers for both 5G New Radio (5G-NR) and Lo

arXiv:2602.08329v2 Announce Type: replace-cross Abstract: A core bottleneck in large language model (LLM) inference is the cost of attending over the ever-growing key-value (KV) cache. Although near-o

Spot on. 'When we got attacked, our team initially turned to frontier closed-source APIs that blocked us because of safeguards that still can’t always tell the difference between attackers and defende

arXiv:2609.29103v1 Announce Type: new Abstract: Accurate state estimation (tracing) of Deformable Linear Objects (DLOs) such as cables is a critical challenge for data centers, manufacturing, construc

Hi people, I am looking for a lightweight IDE or plugin that won't inject large context at initiation. I tried Cline and native VS Code but they inject such heavy initial context that it fills up my g

arXiv:2609.27338v1 Announce Type: new Abstract: Learned local navigation in crowded indoor environments is sensitive to how dynamic obstacle motion is represented, while collision-prone behaviour may

arXiv:2609.28007v1 Announce Type: new Abstract: Most Turkish-capable large language models (LLMs) are evaluated using general-purpose benchmarks rather than long, structurally complex domain documents

Fentanyl Grade Compute: Why a GB300 Rack Will Out-Price Blow by Weight in 2030 A GB300 NVL72 weighs roughly 1,580 kg fully populated and recent purchase orders put it at 5M per rack. That is 3,165/kg.

Ok, so the Mac M5 Ultra (256GB) hit the market, but the only publicly available benchmarks material are flashy YouTube 'clown influencers' videos. We need serious numbers to evaluate whether Apple’s s

arXiv:2609.27118v1 Announce Type: new Abstract: Greenhouse climate management aims to improve crop production while limiting energy use. This requires knowing how a crop will respond before conditions

arXiv:2609.28179v1 Announce Type: new Abstract: GPU robotics lacks the reusable numerical infrastructure of mature CPU stacks, instead relying on compiler frameworks that introduce overhead or repeate

We’re excited and proud to share that Gartner has recognized Google as a Leader for the fourth year in a row in the 2026 Gartner® Magic Quadrant™ for Container Management, based on its Completeness of

arXiv:2609.27449v1 Announce Type: new Abstract: Generalist robot manipulation policies have developed rapidly, yet their reliable evaluation remains challenging due to fundamental flaws in existing si

arXiv:2609.25624v1 Announce Type: cross Abstract: Large language model (LLM) outputs are expected to be reproducible under greedy decoding, yet in practice the same model, prompt, and software stack p