Knowledge catalogue
OpenAI is in deep, deep trouble They are low on capital relative to the massive cash they are burning and there is only so much capital in the world. No rational person would sell their Bitcoin or Nvi
arXiv:2606.04287v1 Announce Type: cross Abstract: Generating realistic and diverse graphs is a key problem in machine learning, with applications in molecular discovery, circuit design, cybersecurity,
arXiv:2606.04511v1 Announce Type: new Abstract: Sparse attention reduces compute and memory bandwidth for long-context LLM inference. However, two key challenges remain: (1) KV cache capacity still gr
arXiv:2606.04246v1 Announce Type: new Abstract: Automatic generation of RTL code for digital hardware designs remains challenging due to long-horizon reasoning, multi-step dependencies, and strict cor
arXiv:2606.04388v1 Announce Type: cross Abstract: Federated Learning (FL) has emerged as an effective paradigm for collaborative intelligence while preserving data privacy. However, data heterogeneity
Together AI provides the inference stack behind both: high-throughput serving on the latest NVIDIA Blackwell GPUs for agentic workloads, and TensorRT engines plus event-driven streaming I/O for low-la
Microsoft Foundry Managed Compute is a new GPU platform-as-a-service for hosting open-source and custom AI models behind the same endpoint, SDKs, and bill as frontier models. The post Announcing Found
The agentic AI era is putting new pressure on the infrastructure stack, and CoreWeave Inc.’s latest milestone gives the conversation a sharper edge. This week, the company announced that it has comple
This article explores the historical development and origins of floating-point number representation in computing, likely covering how early computer scientists and engineers designed methods to repre
arXiv:2606.02857v1 Announce Type: cross Abstract: Zeroth-order (ZO) optimization is a memory-efficient alternative to backpropagation for fine-tuning large language models, but its deployment is limit
arXiv:2606.03014v1 Announce Type: new Abstract: Mixture-of-Agents (MoA) systems improve reasoning accuracy by routing each query to multiple expert LLMs and aggregating their outputs. Efficiently exec
The Information: Nvidia acquired Kumo, which sells predictive AI software to enterprises, a source says for 400M+; PitchBook: Kumo raised 37M at a 250M valuation in 2022 — Nvidia has bought Kumo AI, a
At CVPR, NVIDIA is unveiling new physical AI agent skills that help researchers and developers speed the development of autonomous vehicles, robots and vision AI systems. The core challenge in physica
arXiv:2606.03551v1 Announce Type: new Abstract: Simulation has become a core infrastructure for robotics research. Unlike previous simulators, NVIDIA Isaac Sim leverages GPU acceleration to enable lar
What makes a robot gripper useful isn’t that it can pick up one object — it’s that it can pick up the next one, and the one after that, with a tool it’s never held before. What makes an autonomous veh
arXiv:2606.02608v1 Announce Type: new Abstract: We study a Marchenko--Pastur (MP) random-matrix approach to pruning deep neural networks with very small post-pruning fine-tuning budgets. The main prac
French quantum computing startup Quobly SAS today announced that it has raised €130 million, or about 150 million, to commercialize its technology. The Series A round was led by publicly traded chipma
arXiv:2505.08222v3 Announce Type: replace-cross Abstract: Autonomous vehicles (AVs) offer a cost-effective solution for scientific missions such as underwater tracking. Reinforcement learning (RL) has
arXiv:2606.03681v1 Announce Type: new Abstract: Pretraining cost is a major bottleneck for research on tabular foundation models, slowing the iteration cycle for new architectures, priors, and optimiz
This article explores the potential viability and benefits of locating data centers in space rather than on Earth, likely discussing advantages such as reduced cooling costs due to the vacuum environm
arXiv:2606.02979v1 Announce Type: cross Abstract: We present a novel compact deep multi-task learning model to handle various autonomous driving perception tasks in one forward pass. The model perform
arXiv:2601.21444v2 Announce Type: replace-cross Abstract: The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multim
B9471 is a build release of llama.cpp, an open-source C/C++ implementation for LLM inference that enables running large language models on consumer hardware with optimized performance. This intermedia
arXiv:2606.00144v1 Announce Type: cross Abstract: Speculative decoding speeds up autoregressive decoding by using a drafter to propose multiple tokens that a verifier validates in parallel. In resourc
arXiv:2606.00890v1 Announce Type: new Abstract: Ultrasound is the most widely used real-time imaging modality in clinical practice, yet per-frame video annotation remains a major bottleneck: expert la
arXiv:2603.28768v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) has recently emerged as the mainstream architecture for efficiently scaling large language models while maintaining n
NVIDIA JetPack 7.2 enables deployment of AI agents to edge devices with optimized memory and performance for real-world applications. The release directly supports one-command deployment of NVIDIA Nem
arXiv:2512.10236v2 Announce Type: replace-cross Abstract: Modern ML workloads demand distributing training and inference across multiple GPUs. However, these parallelization techniques often suffer fr
arXiv:2511.04791v2 Announce Type: replace Abstract: Modern LLM serving systems must sustain high throughput while meeting strict latency SLOs across two distinct inference phases: compute-intensive pr
arXiv:2606.01964v1 Announce Type: new Abstract: The way our eyes move while reading provides valuable insights into both the reader's cognitive processes and the properties of the text. In particular,
First technical Deepdive on M3 on the internet😎 MiniMax-M3 combines 1M context, native multimodality, and MiniMax Sparse Attention. The next layer is serving it efficiently: KV-block-major sparse atte
Accelerated computing has revolutionized industrial engineering, compressing simulation times from weeks to hours. Today’s remaining challenges sit in the end-to-end workflow surrounding the simulatio
Lambda workspaces help teams organize cloud resources, control access, and separate dev, staging, and production in shared GPU environments. A junior researcher kills a production training run. A cont
Nous Research is hosting a livestream featuring team members Karan and Yoni speaking from NVIDIA, likely discussing AI research, model development, or collaboration between Nous Research and NVIDIA. T
arXiv:2606.01838v1 Announce Type: cross Abstract: Agentic language model systems alternate between two structurally distinct step types: structured tool calls (short, deterministic, low perplexity) an
arXiv:2606.00228v1 Announce Type: new Abstract: In semiconductor manufacturing, lithography projects circuit layouts onto silicon wafers through an optical mask. As circuit features shrink below the w
arXiv:2606.00946v1 Announce Type: cross Abstract: Efficiently serving large language model (LLM) inference tasks is crucial both for user-perceived latency such as time-to-first-token (TTFT) and for G
Sawdah Bhaimiya / CNBC: Marvell shares closed up 32.52% on Tuesday after Jensen Huang hailed the chipmaker as the “next trillion-dollar company” at Computex — Nvidia's CEO Jensen Huang hailed Marvell
Microsoft Corp. today announced it’s bringing agentic development capabilities into the hands of developers with a new desktop form factor supercomputer called the Surface RTX Spark Dev Box. Developed
MiniMax-M3 combines 1M context, native multimodality, and MiniMax Sparse Attention. The next layer is serving it efficiently: KV-block-major sparse attention, paged MSA decode, optimized index scoring
Agentic AI is getting physical. At COMPUTEX on Tuesday, NVIDIA announced NVIDIA JetPack 7.2 and NVIDIA NemoClaw support on NVIDIA Jetson. JetPack 7.2 brings agentic AI skills, Yocto project support, N
arXiv:2606.01839v1 Announce Type: cross Abstract: LLM-based agents resolve a user task through many turns of dependent inference and tool calls, producing a workload whose total cost is unknown when t
NVIDIA and DigitalOcean are collaborating to develop an open infrastructure stack designed to support autonomous AI agents that operate continuously. The initiative emphasizes open-source principles a
Opus 4.8 likely refers to a software release, update, or feature announcement covered by Ben's Bites, a technology newsletter focused on AI and software developments. Without access to the specific ar
arXiv:2606.02100v1 Announce Type: new Abstract: Transformer models dominate modern NLP, but efficient, language-specific models remain scarce. In Portuguese, most focus on scale or accuracy, often neg
arXiv:2408.11266v5 Announce Type: replace Abstract: Deep learning is now common across many scientific fields, including the study of partial differential equations. This article provides a brief, acc
arXiv:2602.08585v2 Announce Type: replace-cross Abstract: Given the quadratic complexity of attention, KV cache eviction is vital to accelerate model inference. Current KV cache eviction methods typic
Bloomberg: Procurement records show at least seven Chinese universities that support the country's military and defense industry are seeking access to Nvidia's H200 chips — At least seven Chinese univ
arXiv:2503.05641v4 Announce Type: replace-cross Abstract: Combining existing pre-trained LLMs is a promising approach for diverse reasoning tasks. However, task-level expert selection is often too coa
arXiv:2606.01790v1 Announce Type: cross Abstract: Vision-language-model-based graphical user interface (GUI) agents have shown broad automation capabilities, yet deployment is bottlenecked by a key-va
arXiv:2606.00380v1 Announce Type: cross Abstract: Machine unlearning removes the influence of specific training data from a trained model without retraining it from scratch. Evaluating an unlearning m
Teach an agent a workflow once. Have it remember after every rebuild. This tutorial shows how to deploy @nousresearch Hermes Agent with NVIDIA NemoClaw and OpenShell, connect it to Slack, Outlook, Git
The future of design doesn’t interrupt your process. @NousResearch Hermes keeps designers in creative flow - Rhino → ComfyUI → @Blender in one seamless agent workflow. No context switching. Just visio
Ollama 0.30 provides improved compatibility and performance using llama.cpp, augments the MLX engine on Apple Silicon for broader hardware support, and brings support for a wider range of models inclu
200m investment in world model AI R&D and jobs - a warm British welcome to your European HQ, @runwayml @c_valenzuelab 🇬🇧🚀 ANOTHER big AI Lab is massively investing in London. This time it is @runwayml
A lot more to come! We are excited to work closely with NVIDIA on the Cosmos Coalition Introducing the Cosmos Coalition A new global initiative with NVIDIA and leading AI labs to build and open-source
A new beginning of PC starts with @NVIDIARTXSpark, supercharging what's possible in Hermes Agent. This is the NVIDIA RTX Spark Superchip. A new beginning for personal computers. Designed for creators,
If you’re iterating on deploying large language models (LLMs) on AWS GPU instances, you’ve probably noticed the larger the model to be loaded into GPU High Bandwidth Memory (HBM), the longer the painf
AI companies wouldn't enslave engineers, or steal chips from Nvidia, or illegally tap a power line. So why, asks @AGSNYT, do they feel entitled to 'a brazen theft of intellectual property' from news o
arXiv:2605.31481v1 Announce Type: new Abstract: As robot control shifts toward large-scale reinforcement learning with in-loop dynamics computation, the community's reliance on CPU-bound libraries suc