Benchmarking LLM Inference at Scale with AIPerf
NVIDIA AIPerf is a benchmarking framework that supersedes GenAI‑Perf with a multiprocess architecture, eliminating client‑side bottlenecks during high‑concurrency LLM testing. It supports more than 15
Knowledge catalogue
NVIDIA AIPerf is a benchmarking framework that supersedes GenAI‑Perf with a multiprocess architecture, eliminating client‑side bottlenecks during high‑concurrency LLM testing. It supports more than 15
arXiv:2609.19767v1 Announce Type: new Abstract: True machine intelligence requires transcending passive pixel registration to master top-down functional reasoning over absent information via visual ne
arXiv:2609.19934v1 Announce Type: new Abstract: Depth-recurrent language models iteratively apply a small layer stack, decoupling per-token compute from distinct parameter count. To determine whether
arXiv:2609.19842v1 Announce Type: new Abstract: Effective EEG decoding requires representations that preserve organization among channels, local waveform dynamics, and long-range temporal context. Exi
arXiv:2609.19669v1 Announce Type: new Abstract: Adversarial patches to Vision-Language-Action (VLA) policies can cause both immediate action corruption and persistent state effects that remain after t
arXiv:2609.20641v1 Announce Type: cross Abstract: Physics-informed neural networks and finite element methods provide two different paradigms for the numerical approximation of partial differential eq
arXiv:2609.19966v1 Announce Type: new Abstract: Synthetic image and mask pairs can alleviate scarce colonoscopy annotations, but realistic synthesis requires preserving the supplied lesion while gener
Big fan of how @LangChain is doing these insta-webinars The news is a few days old, @typesafeai is integrated and documented with example code in LangChains Docs 👇 And they are doing a webinar on the
arXiv:2609.19875v1 Announce Type: new Abstract: We propose a new probabilistic model for general-purpose medical image registration that builds upon the mutual information registration criterion. It c
arXiv:2609.19881v1 Announce Type: new Abstract: Embodied visual perception relies on temporally coherent visual experience accumulated through continuous engagement with the environment. However, coll
arXiv:2609.19180v1 Announce Type: new Abstract: Language models face unique challenges in analyzing interdisciplinary scientific research literature. In biophysics research, faithful answers require g
arXiv:2609.19242v1 Announce Type: new Abstract: Block diffusion language models (BDLMs) combine autoregressive dependencies across blocks with parallel denoising within blocks, but long-context traini
bonsai claim 98.2% intelligent retained, but their own documents show Ternary Bonsai 2 27B reaches 52.8 and 60.8, respectively, compared with 69.7 and 80.6 for Qwen3.5-27B, retaining roughly three qua
arXiv:2602.16870v2 Announce Type: replace Abstract: The Boreas Road Trip (Boreas-RT) dataset extends the multi-season Boreas dataset to new and diverse locations that pose challenges for modern autono
arXiv:2609.20147v1 Announce Type: cross Abstract: Cortical hypometabolism measured by Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) is a highly sensitive biomarker for dementia diagnosis.
Build your own harness, folks. This is absolute banger paper from NVIDIA on self-evolving agent harnesses. (bookmark it) They introduce SoL-Pi which cuts token traffic by nearly half. And it matches i
arXiv:2509.25248v2 Announce Type: replace-cross Abstract: Automatically compiling open-source software (OSS) projects is a vital, labor-intensive, and complex task, which makes it a good challenge for
arXiv:2607.16682v2 Announce Type: replace-cross Abstract: The widespread adoption of high-level deep learning libraries, while accelerating model development, has increasingly abstracted away the inte
Planning, coding, testing = 8h total. Stack: VSCode Copilot in autopilot mode + SGLang Stats: ∼10k lines generated, ∼800k tokens consumed Sure, it's not GPT-6 Astra level, but for a 100% local ∼180B M
arXiv:2609.19422v1 Announce Type: cross Abstract: Burnout is a chronic occupational syndrome, and open source is close to a worst case for it: maintainers absorb unbounded demand with no manager to re
arXiv:2609.20765v1 Announce Type: new Abstract: Radio Frequency(RF)-Fingerprinting is a spectrum monitoring technique that identifies specific transmitters based on hardware impairments imprinted with
arXiv:2609.20819v1 Announce Type: new Abstract: Perceiving and remembering the visual world is fundamental to navigating and interacting with our environment. Current 4D foundation models, such as cam
arXiv:2609.20027v1 Announce Type: new Abstract: Subliminal learning allows language models to transmit behavioral traits through training data with no obvious semantic relationship to those traits, un
arXiv:2609.19354v1 Announce Type: cross Abstract: Automated action quality assessment (AQA) in Olympic sports remains a challenging task due to the complexity of human motion and the subjectivity inhe
arXiv:2609.20098v1 Announce Type: new Abstract: Reliable temporal-difference targets are central to off-policy actor-critic learning. Direct value improvement refines the next-state target with altern
arXiv:2609.19970v1 Announce Type: new Abstract: Predicting cellular responses to perturbations supports the study of gene function, disease mechanisms, and therapeutic strategies. Despite advances in
arXiv:2609.19606v1 Announce Type: new Abstract: This empirical study is an independent reproduction of the dissociation Zhao reported in 2026. The shape of a large language model's chain-of-thought en
AI is accelerating software development at an unprecedented pace. But as code generation scales, so do the challenges of securing the code, especially emerging AI-based vulnerability exploitations. To
arXiv:2609.19244v1 Announce Type: new Abstract: Conversational LLM agents increasingly rely on Web search, yet the end-to-end lifecycle of agentic search remains poorly understood. We present the firs
According to people familiar with the matter, Naive AI, an AI startup founded in February this year by Tsinghua University professor Dai Jifeng, has completed three funding rounds totaling 400 million
arXiv:2609.20625v1 Announce Type: cross Abstract: Large language model responses are non-deterministic, so failures in LLM agents are hard to reproduce: a failure depends on inference that is not bitw
arXiv:2506.17277v2 Announce Type: replace-cross Abstract: The retrieval stage of retrieval-augmented generation (RAG) for scientific question answering depends on how documents are segmented and how c
arXiv:2609.19911v1 Announce Type: new Abstract: 3D grounding aims to localize target entities in complex scenes from natural language and plays a fundamental role in embodied perception and spatial re
arXiv:2609.19892v1 Announce Type: cross Abstract: As agent systems become more widely used, multiple agent sessions increasingly run alongside pre-existing user tasks in the same environment, sharing
arXiv:2609.20267v1 Announce Type: cross Abstract: Concept erasure aims to selectively eliminate undesired visual semantics from pre-trained generative models without compromising their general utility
arXiv:2609.19585v1 Announce Type: cross Abstract: In mental health care, reasoning over patient journeys is a key task for clinicians. Yet these journeys, encompassing a longitudinal progression of bi
arXiv:2609.19425v1 Announce Type: new Abstract: Tool-augmented large language model (LLM) agents fail in a way no tool-selection or tool-security method addresses: they call tools that do not exist an
arXiv:2609.19923v1 Announce Type: new Abstract: Vision-language-action models (VLAs) have emerged as a promising paradigm for general-purpose robot learning, with performance improving as models and d
arXiv:2609.19199v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly adopted for compliance and legal reasoning tasks, yet their outputs often lack explicit grounding in leg
arXiv:2609.20822v1 Announce Type: cross Abstract: Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controller as a program, and agents built
arXiv:2609.20598v1 Announce Type: new Abstract: In this paper, we tackle the problem of jointly estimating the system states and partially unknown dynamics within distributed sensor-equipped networks,
arXiv:2601.08464v2 Announce Type: replace-cross Abstract: Context-aware building massing is an important early-stage design task: given a site for buildings, a generated massing should not only fit th
arXiv:2510.25595v2 Announce Type: replace-cross Abstract: While Large Language Model (LLM) agents are often approached from the angle of action planning/generation to accomplish a goal (e.g., given by
arXiv:2609.20386v1 Announce Type: new Abstract: Iris presentation attack detection (PAD) is security-critical when a subsystem that appears reliable during development encounters presentation attack i
arXiv:2606.13028v2 Announce Type: replace-cross Abstract: Depth estimation has numerous medical and surgical applications. We benchmark four depth sensors on a porcine bone specimen, a porcine belly s
arXiv:2602.00141v2 Announce Type: replace-cross Abstract: Quark-gluon discrimination provides a useful test case for studying how different machine-learning architectures learn the spatial structure o
arXiv:2609.20352v1 Announce Type: new Abstract: Large-scale routing often requires visiting clusters of nodes in a prescribed order, giving rise to the Ordered Clustered Traveling Salesman Problem (OC
arXiv:2509.09121v2 Announce Type: replace Abstract: Large language models (LLMs) excel in general-domain applications, yet their performance often degrades in specialized tasks requiring domain-specif
arXiv:2609.19976v1 Announce Type: new Abstract: Vision-language-action models tell a robot where to move, but not how hard to push. Contact-rich tasks depend on that second quantity, compliance, yet n
arXiv:2609.19465v1 Announce Type: new Abstract: Compositional reasoning is critical for real-world problem solving: since training data is necessarily limited, models must generalize by composing lear
arXiv:2609.19539v1 Announce Type: cross Abstract: Active subspace methods provide a framework for quantifying predictive uncertainty in high-dimensional models by identifying and performing inference
arXiv:2609.19525v1 Announce Type: cross Abstract: Clinical B-mode images are widely available as potential data sources for quantitative ultrasound (QUS) analysis for tissue characterization. However,
arXiv:2609.19674v1 Announce Type: new Abstract: A learned simulator can reproduce its training conditions accurately yet fail in two distinct ways once those conditions change. Over long rollouts, sma
arXiv:2609.19848v1 Announce Type: new Abstract: Point-feature label placement on interactive maps must reconcile geometric validity, display yield, local placement utility, and stability across camera
arXiv:2609.19789v1 Announce Type: new Abstract: Multi-agent trading systems built on large language models (LLMs) are beginning to appear in quantitative finance, yet their robustness to adversarial i
arXiv:2609.19551v1 Announce Type: new Abstract: In an enterprise system, updating one field can set another, create a record, or start an approval. These effects are produced by business rules that ar
arXiv:2607.09557v2 Announce Type: replace Abstract: Fine grain control and positioning of autonomous underwater vehicles (AUVs) is critical for sampling, maintenance, and survey applications. Traditio
arXiv:2609.19670v1 Announce Type: new Abstract: Direct forecasting has become a standard paradigm for multivariate time-series forecasting because it predicts the full future horizon in a single pass.
arXiv:2609.20586v1 Announce Type: cross Abstract: Referring scene understanding for embodied robots requires grounding object- and relation-centric language queries from a designated viewpoint. While
arXiv:2609.19818v1 Announce Type: cross Abstract: Generalizing to unseen attacks remains challenging for audio deepfake detectors, and collecting training data covering all potential attacks is imprac