Knowledge catalogue
arXiv:2609.23321v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) has become a key technology for serving large-scale personalized large language models and diffusion models in the cloud. H
arXiv:2609.24219v1 Announce Type: new Abstract: Traditionally, the reliability of news publishers is assessed by expert organisations that evaluate editorial practices, transparency and factual standa
arXiv:2609.23966v1 Announce Type: new Abstract: LLMs can generate fluent descriptions from tables, but their outputs may remain logically unsupported by the structured data. We introduce STAT-TO-TEXT,
arXiv:2609.22642v1 Announce Type: cross Abstract: We develop inference for manifold-valued population minimizers when each observation belongs to a different participant and only locally private messa
Meet Wally. Our inference stack for open frontier models, built to be the fastest place to run them. Performance snapshot: GLM-5.3 Flash: 380 tok/s. GLM-5.3 Max: 790 tok/s Qwen3.8-27B: 485 tok/s DeepS
arXiv:2609.21910v1 Announce Type: cross Abstract: We consider nonparametric tangent vector field regression on a Riemannian manifold without boundary. Because responses at different points lie in diff
arXiv:2603.19375v2 Announce Type: replace-cross Abstract: Membership inference attacks (MIAs), which enable adversaries to determine whether specific data points were part of a model's training datase
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
Hot topic livestream: Learn about Jev A buzzy new model Jev, by @typesafeai, reports up to 200x faster inference and 400x lower cost than comparable LLMs on classification tasks. It's aiming to solve
arXiv:2609.19357v1 Announce Type: cross Abstract: We propose a framework for restricted inference on random dot product graphs whose latent positions lie on an unknown low-dimensional support manifold
arXiv:2609.20449v1 Announce Type: new Abstract: The economic value of inference depends on how capacity and task information are distributed across stages of AI production. We study these organization
arXiv:2609.17943v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by attention, whose repeated KV-cache reads make decoding memory-bound. Self-speculative decoding alleviate
arXiv:2609.17573v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) are emerging as a promising generative paradigm that complements autoregressive decoding. In long-context sett
Delos Data Inc., a startup that develops hardware for artificial intelligence clusters, has raised more than 100 million in funding. The capital was provided by Matrix, Playground, Socratic Partners,
arXiv:2508.11584v3 Announce Type: replace-cross Abstract: Deploying multiple machine learning models on resource-constrained robotic platforms for different perception tasks often results in redundant
Confidential Computing keeps your data from being tracked or used in three ways: - End-to-end encrypted inference - Hardware-enforced isolation that extends to the GPU with @nvidia Confidential Comput
arXiv:2609.16085v1 Announce Type: cross Abstract: Eight-bit integer (INT8) post-training quantization is the default recipe for edge deployment, under a widely held assumption: INT8 makes inference fa
arXiv:2609.16841v1 Announce Type: cross Abstract: Increasing image resolution produces ever-longer visual-token sequences in vision-language models (VLMs), substantially raising their inference cost.
arXiv:2609.16722v1 Announce Type: new Abstract: Scaling Multimodal Large Language Models (MLLMs) to long-form video understanding is bottlenecked by the explosion of visual tokens, which saturates con
SemiAnalysis: A deep dive into on-device and data center inference for robots, including a primer on robot models, deployments, supply chains, the “network wall”, and more — Robot Models, Silicon & DR
Anthropic and OpenAI cannot become profitable unless they can reduce the ratio of training cost to inference profits. In the long run, their survival may depend on outlawing competitive open source mo
Kai Nicol-Schwarz / CNBC: Netherlands-based inference chip startup Euclyd raised a €200M+ Series A co-led by Samsung, Somerset Capital, Scaleup Europe Fund, and Innovation Industries — Samsung has bac
arXiv:2609.15021v1 Announce Type: cross Abstract: Shared host-memory caching can avoid repeated prefill when a request moves between inference replicas. Its usefulness depends on both correct state tr
arXiv:2609.11934v1 Announce Type: new Abstract: In networked dynamical systems, the parameter of primary mechanistic interest is signed interaction structure. Recovering this structure from perturbati
The Perplexity Windows app introduces a “Portable Computer” feature—a local‑first AI tool that runs directly on the user’s device. On‑device inference is supported only when the machine has an NVIDIA
arXiv:2609.11969v1 Announce Type: cross Abstract: As the population ages, the number of patients with cardiovascular diseases continues to increase, highlighting the need for early detection before pr
arXiv:2609.12469v1 Announce Type: new Abstract: False wake-up activations remain a persistent challenge in conversational AI. Speech phonetically similar to a device's wake word can produce a syntacti
arXiv:2609.11936v1 Announce Type: cross Abstract: Energy supply and heat dissipation are two of the main challenges with modern GPU deployments. While typically discussed in the context of new datacen
Fast meets open. 🚀 Qwen3.8-27B is now running on @cerebras with rapid inference. Try it now! Qwen3.8-27B is now live at Cerebras speed. The dense, open-weight model from @Alibaba_Qwen scores 34 on the
arXiv:2609.10608v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in generative tasks across various areas, however their training process raises significant privacy
arXiv:2609.11915v1 Announce Type: cross Abstract: Generative artificial intelligence changes how firms reach customers, but standard marketing data do not record how often users see and notice a firm'
🌐 Supporting open source. Expanding deployment options. We’ll work closely with the open-source community on V4.1-Flash inference support and explore more deployment options. Planning a large-scale de
arXiv:2609.08307v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as backends for intelligent web services, but serving them across the edge continuum requires balan
arXiv:2609.05565v1 Announce Type: cross Abstract: Large language model (LLM) sustainability is increasingly a serving-systems problem, not only a training problem. In production, energy and carbon imp
We have just raised 3B€ to accelerate our R&D. We are scaling up our training and inference compute to build future generations of our models, and expanding our Science team across all our offices --
arXiv:2609.04305v1 Announce Type: cross Abstract: We present TNFlow, a transformer and normalizing flow architecture for inferring the surface composition of Trans-Neptunian Objects (TNOs) from their
Been posting individual pieces of RunAnywhere for months. Here's the whole thing in one place. RunAnywhere SDKs is a complete inference suite for any dev who wants to run AI on the user's device. ->8
I always heard that cryptocurrency mining can damage a GPU ( it's maybe wrong) so how much long term inference is damaging a GPU? I mean servers are made for 25/7 operation... Gaming GPUs not so sure?
arXiv:2609.02971v1 Announce Type: cross Abstract: As vehicular networks move toward 5G/6G edge intelligence, federated learning (FL) is widely promoted as a privacy-preserving way for vehicles and inf
arXiv:2606.19264v2 Announce Type: replace-cross Abstract: The knowledge encoded in large language models (LLMs) can serve as a substrate for structured reasoning over variables describing a complex wo
arXiv:2609.02990v1 Announce Type: cross Abstract: To scale up collective decision-making, participatory democracy platforms such as Polis and Remesh enable online deliberation among thousands of parti
arXiv:2607.09791v2 Announce Type: replace-cross Abstract: The multiplicative repetition penalty shipped across the LLM inference ecosystem (HuggingFace, vLLM, llama.cpp, and a dozen further engines) b
Bloomberg: Sources: Crusoe signed a ~$13B, five-year deal with Jane Street to provide GPUs and other infrastructure for AI training and inference via its cloud platform — Crusoe, a data center upstart
arXiv:2508.04080v2 Announce Type: replace Abstract: Standard large language model prompting treats geospatial inference as independent, instance-wise prediction, ignoring the fundamental spatial depen
Lily treats Apple silicon as a distinct inference platform and maps Qwen’s operations directly to its compute and memory architecture. Lily is now available: https://github.com/perplexityai/pplx-garde
arXiv:2609.00624v1 Announce Type: new Abstract: A prominent paradigm in inference-time alignment employs lightweight supervisors to steer Large Language Models (LLMs). Through empirical analysis, we i
arXiv:2310.04363v3 Announce Type: replace-cross Abstract: Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions. This lim
arXiv:2210.00580v4 Announce Type: replace Abstract: This paper builds bridges between two families of probabilistic algorithms: (hierarchical) variational inference (VI), which is typically used to mo
arXiv:2310.08774v3 Announce Type: replace-cross Abstract: Phylogenetics is a branch of computational biology that studies the evolutionary relationships among biological entities. Its long history and
arXiv:2603.25201v2 Announce Type: replace Abstract: Recent research points toward LLMs being manipulated through adversarial and seemingly benign inputs, resulting in harmful, biased, or policy-violat
arXiv:2608.30395v1 Announce Type: new Abstract: As pretraining scaling laws approach saturation, Test-Time Scaling (TTS) has emerged as an important direction for improving reasoning by allocating inf
arXiv:2608.27460v1 Announce Type: new Abstract: Large output embedding matrices create a significant memory bandwidth bottleneck during autoregressive decoding, especially for compact LLMs with large
arXiv:2608.26998v1 Announce Type: new Abstract: Intracranial electroencephalography (iEEG) provides temporally precise and spatially specific access to neural activity from focal and deep brain region
arXiv:2608.24136v1 Announce Type: new Abstract: Recurrent models, which repeatedly update latent states with shared computation blocks, have emerged as powerful architectures for solving complex reaso
arXiv:2607.27910v2 Announce Type: replace Abstract: Inference time defences against vision language model jailbreaks often subtract a calibrated direction from the residual stream at a chosen decoder
arXiv:2608.22066v1 Announce Type: cross Abstract: Attention-based multiple instance learning (ABMIL) using pathology foundation model embeddings is effective for slide-level tasks, but exhaustive infe
arXiv:2608.23375v1 Announce Type: cross Abstract: Gumbel-based inference verification bounds LLM weight exfiltration by only forgiving token choices that plausibly arise from honest GPU nondeterminism
Eugene Demaitre / The Robot Report: Nvidia unveils the Jetson Orin Nano 2 edge AI computer that it says doubles inference performance, with 78 TOPS of AI compute and an eight-core Arm CPU — As AI mode
arXiv:2608.20999v1 Announce Type: new Abstract: Multimodal LLMs apply the language model interface to visual inputs, where ordinal regression tasks such as age estimation, image quality assessment, an
Has anyone else experimented with ubatch size when running GLM-5.2 locally? I was testing the 226 GiB GLM-5.2-UD-IQ2_XXS GGUF on 3x RTX PRO 6000 Blackwell GPUs and got a pretty interesting result. Wit