Knowledge catalogue
arXiv:2508.12021v2 Announce Type: replace Abstract: Unsupervised federated learning (UFL) enables privacy-preserving distributed training without data labeling, yet practical deployment remains challe
arXiv:2610.06621v1 Announce Type: new Abstract: Spectral variants of low-rank adaptation (LoRA) choose both a subspace and which factor to freeze. We separate these choices by freezing the input facto
arXiv:2610.03817v1 Announce Type: cross Abstract: Purpose: To evaluate the performance-feasibility tradeoffs of foundation models (FMs) and task-specific convolutional neural networks (CNNs) trained f
arXiv:2610.05051v1 Announce Type: new Abstract: Time-series data are often sampled irregularly at high frequencies and exhibit long-range dependencies, which makes long-horizon modelling difficult. Co
arXiv:2610.06801v1 Announce Type: new Abstract: Sparse attention is a primary approach to reducing the latency of diffusion transformers in long-sequence generation tasks, such as video and high-resol
arXiv:2610.05458v1 Announce Type: new Abstract: Running the same language model on different graphics processing unit (GPU) vendors can produce different logits, even when the model weights and inputs
arXiv:2610.05014v1 Announce Type: new Abstract: Recent GPU kernel optimization agents retain what they learn in knowledge bases or as distilled skills. Kernel benchmarks score each attempt's implement
arXiv:2610.04014v1 Announce Type: new Abstract: We introduce the first learned articulated body simulator based on a selective state space model (SSM), called PhysMamba. PhysMamba predicts next-frame
Reflection AI Inc. today introduced Beam, an open-source large language model with 501 billion parameters. The launch comes a few months after the startup raised funding at a 25 billion valuation. Aro
arXiv:2610.05683v1 Announce Type: cross Abstract: AI systems can now write and optimize production GPU kernels, but validating them remains an important challenge. Evaluating the kernel on a few rando
arXiv:2610.06087v1 Announce Type: new Abstract: Game-theoretic attribution explains a model by assigning credit to its features or training examples. The least core has attracted interest as an altern
arXiv:2610.04403v1 Announce Type: cross Abstract: Post-training quantization to the GGUF format's mixed-precision K-quants is commonly how open-weight language models reach consumer hardware, yet its
Megatron‑LM PR #7262 introduces a workflow that records ordered per‑rank tensor fingerprints to pinpoint and correct nondeterminism in large‑scale pretraining. By implementing low‑overhead kernel twea
Financial Times: Sources: SpaceX is seeking to raise 40B, including ~10B in bank loans and ~$30B in investment-grade debt, to purchase Nvidia chips, in a deal led by Apollo — Blockbuster debt deal is
arXiv:2610.04912v1 Announce Type: cross Abstract: Language models increasingly serve prompts that carry private data, and secure inference under homomorphic encryption lets a client outsource the comp
arXiv:2610.04781v1 Announce Type: new Abstract: In an image latent space, the embeddings of high-resolution, natural, and sharp images form a manifold. Degradation of high-resolution images pushes the
Someone who has always loved looking at the space between different AI techniques, this time I went a little deeper into the memory trade-offs between RNNs, Transformers and SSMs. I found it interesti
arXiv:2610.06063v1 Announce Type: new Abstract: Semantic segmentation of street panoramas can support detailed descriptions of urban environments, yet small datasets and unequal training costs make mo
Telecom operators are increasingly building their AI strategies on open models — and the reasons go beyond mere cost. Open models give telcos the ability to trust, control and customize AI across thei
This past year, OpenAI, Anthropic, and other labs have announced breakthroughs on numerous long-standing mathematical problems, in some cases pushing well beyond what researchers expected current syst
Anthropic’s paid subscription plans deliver more than five‑times the perceived value of comparable OpenAI offerings when evaluated by cost per inference unit and overall revenue contribution. The heav
arXiv:2610.02638v1 Announce Type: new Abstract: Full-duplex voice agents make many small, closed decisions, which current systems answer by slow autoregressive decoding. We propose DuplexJev, which fe
Congrats to the Reflection team on Beam 🎉 Be sure to join us next week at our NYC meet-up with the Reflection team and NVIDIA https://luma.com/TAIxNvidiaxReflection Introducing Beam: a highly efficien
arXiv:2610.02882v1 Announce Type: cross Abstract: Large-scale foundation models achieve strong performance across diverse tasks, but their size makes inference costly, largely due to dense matrix mult
arXiv:2610.02795v1 Announce Type: new Abstract: Deep graph learning models deployed in real-world systems often need to cope with non-stationary environments, where the underlying graph distribution d
Enterprise artificial intelligence software company Iterate Studio Inc. today launched Lifeboat, an inference engine for large language models that has confidential computing built in. Iterate.ai says
arXiv:2610.02395v1 Announce Type: new Abstract: Streaming GPU solvers for entropic optimal transport (EOT), such as FlashSinkhorn, avoid storing the dense kernel but still evaluate all nimes m point p
Breast cancer is the most commonly diagnosed cancer among American women — yet the gaps in care are wide. A majority of women over age 40 skip the recommended annual screening. Radiologists are readin
Dominic-Madori Davis / TechCrunch: Ghost, which makes a 3,499 computer designed for AI agents and includes an RTX Pro 4000 SFF Blackwell GPU, emerges from stealth with an 11M seed led by a16z — For mu
arXiv:2610.03453v1 Announce Type: cross Abstract: Physics simulators and motion planners require convex collision geometry, yet image-to-3D generative models output dense, frequently non-manifold visu
arXiv:2610.03187v1 Announce Type: cross Abstract: Multi-camera streaming perception is increasingly deployed on heterogeneous edge platforms shared with co-resident workloads, yet accelerator placemen
AI data infrastructure must support growing GPU clusters while making enterprise data usable for models and agents. NetApp Inc. is tying intelligent data infrastructure to production AI through a unif
Agentic AI infrastructure must support the work between a model’s decisions as agents move from answering questions to executing tasks. Central processing units handle much of that execution, while gr
Hi folks, LIVE PROJECT PAGE TLDR: Moral of the story. You need better CPU to do actual agentic coding doing real work... I've been on a mission to make my RTX5090 go brrr for past 2 months so much so
arXiv:2610.02911v1 Announce Type: cross Abstract: Methods for training language models on stale samples are judged by comparisons against importance-corrected baselines. We show that details of the ex
Marina Temkin / TechCrunch: Sources: AI inference-chip startup Etched is in early talks to raise funding at a 40B-50B valuation, up from 21B in August — Although it's only been a couple of months sinc
Explore how Microsoft and NVIDIA are helping organizations advance sovereign AI with greater control, choice, flexibility, and resilience across cloud, edge, and customer-controlled environments. The
arXiv:2610.03027v1 Announce Type: cross Abstract: The key-value (KV) cache becomes a major memory bottleneck in long-context LLM inference, placing substantial pressure on memory capacity and bandwidt
The difference in what Anthropic and OpenAI as well as many others give you in value for a subscription is insane. We tested Meta, Minimax, Kimi, Grok, and Cursor subscriptions It doesn't make sense t
arXiv:2610.02468v1 Announce Type: cross Abstract: We present Windfoil, a GPU-friendly algorithm that treats rasterisation and differentiable vector graphics as two sides of the same problem by evaluat
Yann LeCun's latest talk at ETH Zürich 'You should not work on LLM. At least if you're in academia, you should absolutely not work on LLMs. There is nothing you can bring to the table. If you're inter
Mishal Husain / Bloomberg: Q&A with Google SVP and DeepMind Institute co-director James Manyika on AI risks and why responsibility must be shared across industry, government, and society — The accord,
Bradley Olson / Axios: Sources: several Western open-weight models are set to launch this month, including Reflection AI's first model, which will rival top Chinese open-weight models — A closely watc
Meir Orbach / CTech: Nasdaq-listed neocloud Nebius acquires Inferize, whose tech helps optimize GPU utilization and reduce AI request costs, sources say for 100M to 150M — The Israeli startup, which w
Banger paper from NVIDIA on long running agents. A model can accept 128K tokens of context and still make more mistakes the longer it works through a task. If your agent loses its place partway throug
arXiv:2610.00321v1 Announce Type: cross Abstract: Speculative decoding accelerates large language model inference by drafting future tokens cheaply and verifying them with the target model in parallel
arXiv:2610.01439v1 Announce Type: new Abstract: Parallel drafting reduces the drafting overhead of speculative decoding for large language models (LLMs), but its gains remain limited by the accepted p
arXiv:2610.01967v1 Announce Type: new Abstract: As large language models (LLMs) keep growing in size and complexity, their training frameworks evolve at a rapid pace as well. Therefore, continuous int
I've been experimenting with running larger models locally with Ollama, mainly because I'm interested in using them for agentic coding. I kept seeing benchmarks expressed as something like: 40 tokens/
arXiv:2610.01445v1 Announce Type: new Abstract: UMAP achieves scalable layout optimization through stochastic negative sampling. However, this stochasticity can lead to unstable embeddings across reru
arXiv:2610.01468v1 Announce Type: cross Abstract: Low-cost NAS must both explore high-performing architectures and identify them reliably, yet reducing evaluation cost often weakens the fidelity of ca
Hi, i got QFN running on my single r9700 but im not sure if i did everything right to get the best quality and speed out of this setup. Dont want to annoy anybody, maybe someone with the same card can
arXiv:2602.12630v2 Announce Type: replace-cross Abstract: Most large language models (LLMs) run on external clouds: users send a prompt, pay for inference, and must trust that the remote GPU executes
The Comfy Dev Platform Challenge is open! Partners: @ltx_io & @bfl_ai For two weeks (10/5–10/19), we're challenging the community to open-source a paid AI feature. 🏆 $10K grand prize 🖥️ 3x NVIDIA RTX
arXiv:2610.01022v1 Announce Type: new Abstract: Memory-attention-based Video Instance Segmentation (VIS) methods have demonstrated strong zero-shot tracking capability, yet their substantial memory re
arXiv:2610.01959v1 Announce Type: cross Abstract: Path finding and multi-robot motion planning require trajectories that are smooth, goal-directed, and collision-free in environments with complex geom
The neocloud market is moving past its origins as a stopgap for scarce graphics processing units. AI-native startups now choose their infrastructure on latency, burst capacity and openness, not just c
arXiv:2609.38438v1 Announce Type: cross Abstract: Machine learning surrogate models offer a promising path toward accelerating plasma turbulence simulations. We present PreVAE-Turb, a surrogate modeli
arXiv:2609.39111v1 Announce Type: new Abstract: Human intelligence relies heavily on learned intuition: recognising patterns and judging situations without explicitly unfolding every intermediate step
Learn how to use Amazon S3 Vectors as the persistent memory layer within the NVIDIA NeMo Agent Toolkit (NAT), deployed on Amazon Elastic Kubernetes Service (Amazon EKS). This post shows how NAT's memo