Knowledge catalogue
arXiv:2608.20532v1 Announce Type: new Abstract: NVIDIA provides a SASS disassembler but no public SASS assembler for recent data-center GPUs, limiting controlled machine-code rewriting. We present F2A
arXiv:2608.20350v1 Announce Type: cross Abstract: Traditional industrial agents rely on modular pipelines, including Router, Retriever, Planner, Executor, Responder, Reviewer, and other components. Th
arXiv:2608.05944v1 Announce Type: cross Abstract: We report operational experience full-fine-tuning a 32.76B-parameter dense model (Qwen3-32B) on 16 x NVIDIA B300 (two nodes, FSDP / ZeRO-3) -- among t
arXiv:2608.06088v1 Announce Type: new Abstract: Robotics simulators serve as a foundational infrastructure for embodied AI, facilitating safe and scalable robotic system development. NVIDIA Isaac Sim
arXiv:2607.20709v1 Announce Type: new Abstract: Traditional agent development is split across prompt templates, tool schemas, callback code, and workflow graphs. We present NVIDIA Object-Oriented Agen
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
arXiv:2506.01969v3 Announce Type: replace-cross Abstract: Efficient inference of Multi-Head Latent Attention (MLA) is challenged by deploying the DeepSeek-R1 671B model on a single Multi-GPU server. T
arXiv:2606.03159v1 Announce Type: cross Abstract: As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck. In closed-lo
arXiv:2608.24199v1 Announce Type: new Abstract: Generative simulation for surgical robotics still lacks real-time interaction. Physical-robot experiments, often involving animal or cadaver labs, are t
arXiv:2608.08522v1 Announce Type: new Abstract: Event-based vision is becoming an increasingly important sensing paradigm for robotics, yet its adoption remains limited by sensor availability and the
arXiv:2608.08287v1 Announce Type: new Abstract: GPU language comparisons are almost always run on tiled dense linear algebra, where every toolchain is good and the differences are small. We implement
arXiv:2509.22685v2 Announce Type: replace-cross Abstract: Fringe projection profilometry (FPP) is a high-precision structured-light sensing technique for 3D surface reconstruction, yet its practical d
arXiv:2601.20115v3 Announce Type: replace-cross Abstract: As the role of modern Graphics Processing Units (GPUs) becomes increasingly essential for several computing tasks, analyzing their past and cu
arXiv:2601.22813v2 Announce Type: replace Abstract: The NVFP4 lower-precision format, supported in hardware by NVIDIA Blackwell GPUs, promises to allow, for the first time, end-to-end fully-quantized
arXiv:2605.27599v1 Announce Type: cross Abstract: Agentic AI workloads - where a single user goal triggers multi-step orchestration, tool calls, retries, and failure recovery - are being targeted for
arXiv:2610.04949v1 Announce Type: new Abstract: Reinforcement learning controllers for underwater vehicles are usually trained against one physics representation and deployed against another, so repor
arXiv:2608.10103v1 Announce Type: cross Abstract: High-performance Tensor Core kernels rely on a low-level PTX pipeline built from asynchronous data movement with cp.async, warp-level matrix loads wit
arXiv:2608.07226v1 Announce Type: cross Abstract: Compact AI systems make local language-model experimentation increasingly accessible, yet practical evidence for multi-node training on desktop-class
arXiv:2607.19353v1 Announce Type: new Abstract: Confidential computing is becoming a practical deployment requirement for AI inference workloads that process sensitive inputs or protect proprietary mo
arXiv:2607.08098v1 Announce Type: new Abstract: Event cameras offer microsecond temporal resolution, low latency, and high dynamic range, making them attractive for robotics. However, labeled event-ca
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:2505.16968v4 Announce Type: replace-cross Abstract: Cross-architecture GPU code transpilation is essential for unlocking low-level hardware portability, yet no scalable solution exists. We intro
arXiv:2605.16259v1 Announce Type: cross Abstract: While real-time image generation using diffusion models has advanced rapidly on NVIDIA GPUs, systematic optimization research on non-CUDA platforms su
arXiv:2603.20421v2 Announce Type: replace-cross Abstract: We present Hawkeye, a system for analyzing and reproducing GPU-level arithmetic operations. Using our framework, anyone can re-execute on a CP
arXiv:2603.01960v2 Announce Type: replace-cross Abstract: TiledAttention is a scaled dot-product attention (SDPA) forward operator for SDPA research on NVIDIA GPUs. Implemented in cuTile Python (TileI
arXiv:2604.26103v1 Announce Type: cross Abstract: All current LLM serving systems place the GPU at the center, from production-level attention-FFN disaggregation to NVIDIA's Rubin GPU-LPU heterogeneou
arXiv:2604.23466v1 Announce Type: cross Abstract: NVIDIA's CUDA Tile (CuTile) introduces a Python-based, tile-centric abstraction for GPU kernel development that aims to simplify programming while ret
arXiv:2604.24169v1 Announce Type: new Abstract: 3D point cloud perception remains tightly coupled to custom CUDA operators for spatial operations, limiting portability and efficiency on non-NVIDIA, AM
arXiv:2511.10909v2 Announce Type: replace-cross Abstract: Modern AI accelerators rely on matrix multiply-accumulate units (MMAUs), such as NVIDIA Tensor Cores and AMD Matrix Cores, to accelerate deep
arXiv:2603.22126v3 Announce Type: replace Abstract: Deploying learned robot manipulation policies in industrial settings requires rigorous pre-deployment validation, yet exhaustive testing across high
arXiv:2609.33586v1 Announce Type: new Abstract: On NVIDIA Blackwell B200, tensor-core throughput outpaces special-function exponential throughput by more than two orders of magnitude, exposing exponen
arXiv:2609.30846v1 Announce Type: new Abstract: In this paper, we propose I-Parakeet, an integer-only implementation of NVIDIA's Parakeet-CTC (0.6B parameters) that runs on a smartphone NPU without an
arXiv:2609.31383v1 Announce Type: cross Abstract: End-to-end driving policies are commonly trained through open-loop behavior cloning, yet they must ultimately operate in closed-loop when deployed on
arXiv:2609.30854v1 Announce Type: cross Abstract: Autoregressive LLM inference at long context is bounded by memory bandwidth, not arithmetic throughput, and the binding resource shifts from model wei
arXiv:2609.17564v1 Announce Type: new Abstract: Deploying retrieval-augmented generation (RAG) on commodity GPUs such as the NVIDIA T4 (16 GB VRAM) exposes a practical failure mode we call the Compres
arXiv:2609.18310v1 Announce Type: new Abstract: We introduce Nemotron-SEA-LION-v4.8, a family of Southeast Asian Languages in One Network (SEA-LION) built upon NVIDIA Nemotron 3. The family includes 3
arXiv:2609.02684v1 Announce Type: new Abstract: Deploying 3D point cloud models on edge hardware such as the NVIDIA Jetson Orin Nano is severely constrained by compute and memory budgets. Existing com
arXiv:2609.02846v1 Announce Type: new Abstract: Stable 4-bit floating-point (FP4) pretraining is difficult because the E2M1 payload represents only a narrow range of magnitudes. NVIDIA's Transformer E
arXiv:2608.30076v1 Announce Type: new Abstract: Single-GPU deployment of 70B-parameter language models on an NVIDIA GPU is constrained by device memory, long-context throughput, and engineering integr
arXiv:2608.28113v1 Announce Type: new Abstract: The NVIDIA Blackwell architecture, with native support for the ultra-fine-grained NVFP4 format, opens new opportunities for accelerating large language
arXiv:2608.25192v1 Announce Type: new Abstract: We introduce CRESSim-Neo, a batched GPU simulation engine for surgical robotics and robot learning. CRESSim-Neo combines position-based simulation of ri
arXiv:2608.24935v1 Announce Type: new Abstract: Accurate identification of early-stage apple fruitlet anatomical structures, including the calyx, fruitlet body, and peduncle, is essential for robotic
arXiv:2608.17744v1 Announce Type: new Abstract: Take three frontier mixture-of-experts models (Alibaba, OpenAI, NVIDIA; 3.6-4.0B active parameters each) and fine-tune them to reason in a low-resource
arXiv:2608.05138v1 Announce Type: cross Abstract: Modern Greek is absent from NVIDIA's Nemotron retrieval models and from major multilingual retrieval benchmarks, despite being important for retrieval
arXiv:2608.05033v1 Announce Type: cross Abstract: Sparse matrix kernels are fundamental to scientific computing, graph analytics, and machine learning. Their GPU performance depends strongly on the in
arXiv:2607.06202v1 Announce Type: cross Abstract: The deployment of Mixture-of-Experts (MoE) models on production high-bandwidth superpods, such as NVIDIA's NVL72/576 and Huawei's CloudMatrix384, intr
arXiv:2606.23672v2 Announce Type: replace Abstract: This paper presents our algorithmic innovations for the NVIDIA Nemotron Model Reasoning Challenge, focusing on Bit Manipulation Puzzles. In this tas
arXiv:2606.23698v1 Announce Type: cross Abstract: NVIDIA's Blackwell Ultra (B300) cuts FP64 vector throughput to ~1.3 TFLOPS per GPU, roughly 30x below B200 and well below the level at which bandwidth
arXiv:2605.11255v1 Announce Type: new Abstract: We present Hebatron, a Hebrew-specialized open-weight large language model built on the NVIDIA Nemotron-3 sparse Mixture-of-Experts architecture. Traini
arXiv:2605.00519v2 Announce Type: cross Abstract: The operational landscape of local Large Language Model (LLM) inference has shifted from lightweight models to datacenter-class weights exceeding 70B
arXiv:2610.08618v1 Announce Type: cross Abstract: A robot that offloads its control loop to the network carries the receiver with it, so link quality is decided by where it goes. Simulating this requi
arXiv:2609.38216v1 Announce Type: new Abstract: Existing benchmarks evaluate tabletop manipulation, flat-floor household activity, or humanoid locomotion and manipulation as separate task groups; none
arXiv:2609.20034v1 Announce Type: cross Abstract: We present Astronex-World 1.0, an open controllable video world-model foundation. Given a text prompt (text-to-video) or an initial observation (image
arXiv:2408.15538v4 Announce Type: replace Abstract: While modern Autonomous Vehicle (AV) systems can develop reliable driving policies under regular traffic conditions, they frequently struggle with s
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:2509.25180v3 Announce Type: replace Abstract: Existing text-to-image diffusion models excel at generating high-quality images, but face significant efficiency challenges when scaled to high reso
arXiv:2609.08368v1 Announce Type: new Abstract: We present Miles v0.1, a full-stack, production-ready system for frontier post-training. Building upon the clean design of slime, Miles designs each sta
arXiv:2608.21764v1 Announce Type: cross Abstract: Event-based vision has emerged as a promising paradigm for energy-aware artificial intelligence (AI), offering sparse, low-latency visual signals that
arXiv:2608.21887v1 Announce Type: cross Abstract: Runtime thermal management of high-performance chips depends on fast and accurate full-chip thermal maps. Conventional simulators typically estimate p
arXiv:2608.19085v1 Announce Type: cross Abstract: Anticipating how scenes evolve under ego actions is fundamental to safe autonomous driving, yet the full potential of world models for decision-making