Knowledge catalogue
arXiv:2604.27892v1 Announce Type: cross Abstract: The rapidly expanding artificial intelligence (AI) industry has produced diverse yet powerful prediction tools, each with its own network architecture
arXiv:2602.17697v2 Announce Type: replace Abstract: Large Language Models (LLMs) are being increasingly used across a wide range of tasks. However, their substantial computational demands raise concer
arXiv:2604.23709v1 Announce Type: new Abstract: Single image dehazing is often constrained by a trade-off between restoration quality and computational efficiency. While efficient, CNN networks strugg
arXiv:2604.21361v1 Announce Type: new Abstract: Distributed AI inference pipelines rely heavily on timestamp-based observability to understand system behavior. This work demonstrates that even small c
arXiv:2604.20735v1 Announce Type: new Abstract: Accurate condition monitoring of industrial equipment requires inferring latent degradation parameters from indirect sensor measurements under uncertain
arXiv:2604.20775v1 Announce Type: new Abstract: Trajectory Inference (TI) seeks to recover latent dynamical processes from snapshot data, where only independent samples from time-indexed marginals are
arXiv:2604.20420v1 Announce Type: cross Abstract: AI research often emphasizes model design and algorithmic performance, while deployment and inference remain comparatively underexplored despite being
This DigitalOcean guide covers strategies and best practices for deploying and optimizing very large language models (600 billion+ parameters) on cloud infrastructure, focusing on inference performanc
arXiv:2601.22002v3 Announce Type: replace Abstract: Transformers achieve superior performance on many tasks, but impose heavy compute and memory requirements during inference. This inference can be ma
arXiv:2604.18310v1 Announce Type: cross Abstract: Variational inference (VI) is a central tool in modern machine learning, used to approximate an intractable target density by optimising over a tracta
arXiv:2604.15787v1 Announce Type: cross Abstract: We introduce EVIL (extbf{EV}olving extbf{I}nterpretable algorithms with extbf{L}LMs), an approach that uses LLM-guided evolutionary search to discover
arXiv:2604.15672v1 Announce Type: cross Abstract: Speculative decoding (SD) accelerates language model inference by drafting tokens from a cheap proposal model and verifying them against an expensive
arXiv:2604.15488v1 Announce Type: cross Abstract: Large language models (LLMs) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offer
arXiv:2604.14332v1 Announce Type: new Abstract: Diffusion-model inference and overdamped Langevin dynamics are formally identical. A physical substrate that encodes the score function therefore equili
Instead of the gold standard, we can imagine an inference standard of exchange, the FLOP. (As opposed to tokens, this accounts for AI ability) With some AI help, I figure 1 buys roughly 10^17 managed-
arXiv:2510.00310v3 Announce Type: replace Abstract: Federated inference, in the form of one-shot federated learning, edge ensembles, or federated ensembles, has emerged as an attractive solution to co
arXiv:2410.15001v5 Announce Type: replace Abstract: Scalability of Graph Neural Networks (GNNs) remains a significant challenge. To tackle this, methods like coarsening, condensation, and computation
arXiv:2403.03208v3 Announce Type: replace-cross Abstract: Inspired by the concept of active learning, we propose active inferencenicode{x2013}a methodology for statistical inference with machine-l
arXiv:2610.21657v1 Announce Type: cross Abstract: Flow matching has emerged as a powerful generative family for simulation-based inference (SBI). However, sampling and density evaluation require numer
arXiv:2610.21257v1 Announce Type: cross Abstract: Large Language Models (LLMs) demand efficient inference, where the multiply-accumulate (MAC) operations in linear projections dominate compute and ene
arXiv:2610.21892v1 Announce Type: new Abstract: We propose the Graph Dirichlet Energy Causal Inference (GDECI) criterion for distinguishing cause from effect in bivariate settings. For a candidate dir
Agentic workflows are making speed a condition for whole classes of AI applications to exist, and the fastest tokens will determine which platforms win the next phase of AI. Cerebras Systems Inc., whi
arXiv:2610.19053v1 Announce Type: new Abstract: Inference of phylogenetic trees from sequences plays a central role in understanding evolutionary relationships, with applications ranging from tracking
arXiv:2610.14815v1 Announce Type: cross Abstract: Industrial IoT sensors produce continuous, high-volume data streams that predictive maintenance needs to analyse in real time. Cloud-centric architect
arXiv:2610.18617v1 Announce Type: new Abstract: An embodied agent must prioritise among competing bodily needs. In active inference, it can respond to an urgent need by increasing the precision of inf
arXiv:2610.18209v1 Announce Type: new Abstract: Cross-domain few-shot action recognition (CD-FSAR) aims to recognise unseen action classes in a target domain from a handful of labelled videos. Despite
arXiv:2606.17192v2 Announce Type: replace Abstract: This paper develops constrained diffusion models with primal-dual inference (PDI) to sample from optimal distributions of entropy-regularized optimi
ICYMI from yesterday's @dealbook: inference startups are ripping as enterprises continue to adopt AI - @togethercompute's annual bookings hit 1.2 billion as of July - @FireworksAI_HQ crossed 1 billion
arXiv:2601.13155v3 Announce Type: replace-cross Abstract: Long-context inference enhances the reasoning capability of Large Language Models (LLMs), but incurs significant computational overhead. Token
arXiv:2610.10909v1 Announce Type: cross Abstract: Membership inference attacks (MIAs) threaten the privacy of machine learning (ML) training data by determining whether a sample was used to train a ta
arXiv:2610.08917v1 Announce Type: new Abstract: While vision-language-action (VLA) models have advanced rapidly, running them at every control step remains expensive. Prior work accelerates VLA infere
TornadoVM: The Java to CUDA engine: https://github.com/beehive-lab/TornadoVM jitLLM: The inference engine: https://github.com/beehive-lab/jitllm Deep dive talk: https://www.youtube.com/watch?v=HO5CpET
arXiv:2610.06978v1 Announce Type: new Abstract: Gaussian Belief Propagation (GBP) is a distributed inference algorithm that passes messages in graphical models, making it attractive for scalable spati
arXiv:2610.07037v1 Announce Type: new Abstract: AlphaFold 3-style cofolding models predict biomolecular complexes with high structural accuracy, yet a large fraction of their outputs are physically in
arXiv:2610.07587v1 Announce Type: new Abstract: LLM orchestration investigates how an orchestrator coordinates a group of autonomous agents to achieve common goals or maximize collective welfare. The
arXiv:2610.08715v1 Announce Type: cross Abstract: The following motif is common in spatiotemporal settings: we have a sequence of covariate and label pairs observed for a relatively short, recent time
arXiv:2610.08078v1 Announce Type: cross Abstract: Standard causal identification methods often assume no unmeasured confounding and can fail when relevant confounders are unobserved. Proximal causal i
arXiv:2610.03741v1 Announce Type: cross Abstract: Distributed mixture-of-experts (MoE) inference is a promising architecture for deploying large language models (LLMs) at wireless edge networks becaus
arXiv:2610.03939v1 Announce Type: new Abstract: Many inference workloads evaluate a trained tree ensemble on row groups that share feature values: discrete-time survival models expand each patient int
arXiv:2610.02774v1 Announce Type: new Abstract: Long-form generators for music, motion and video produce sequences chunk by chunk, with each chunk generated by iterative denoising while rewards are de
arXiv:2610.02986v1 Announce Type: new Abstract: Membership inference on large language models (LLMs) aims to determine whether a given text sample was included in an LLM's training data, without acces
if you’re building an ai app, you might want to host inference to improve your margins, and if you do that you should support a few models, and if you’re doing that you might as well build a router, a
arXiv:2610.01763v1 Announce Type: new Abstract: Activation sparsity speeds up large language model (LLM) inference by setting unimportant activations to zero so that the corresponding computations can
arXiv:2609.38437v1 Announce Type: new Abstract: Teleoperation systems are tuned for channel fidelity, while whether the operator experiences the device as part of the body, the Sense of Embodiment (So
arXiv:2609.39091v1 Announce Type: cross Abstract: Inference-time alignment of flow and diffusion-based models is critical for achieving flexible generative modeling. Theoretically, Doob's h-transform
Token economics are becoming a defining measure of artificial intelligence infrastructure efficiency. As AI workloads move beyond training, the economics of producing useful intelligence are starting
arXiv:2605.06206v2 Announce Type: replace Abstract: Mixture of experts has emerged as the primary mechanism for making Large Language Models (LLMs) computationally efficient. However, in distributed s
arXiv:2609.35947v1 Announce Type: new Abstract: Many inference-time tasks for pretrained discrete diffusion models and diffusion language models reduce to drawing samples from a tilted version of the
arXiv:2609.37935v1 Announce Type: cross Abstract: Deep Support Vector Data Description (Deep SVDD) has become a prominent framework for unsupervised anomaly detection by learning latent representation
arXiv:2609.35352v1 Announce Type: new Abstract: Fully homomorphic encryption (FHE) enables neural network inference directly on encrypted inputs, but it remains orders of magnitude slower than plainte
Forlinx Embedded has listed an M.2 AI accelerator card based on Rockchip’s RK1820 and RK1828 processors, providing 20 TOPS of INT8 computing performance and up to 5GB of integrated DRAM. The module us
arXiv:2609.34156v1 Announce Type: new Abstract: Prediction-powered inference (PPI) and its power-tuned extension (PPI++) improve confidence intervals by combining a small gold-standard labeled sample
Today I present a fine piece of engineering, carefully assembled inside a custom chipboard chassis: the 2400cc Inference Racer, a.k.a. my winter heater. Power comes from two second-hand AORUS RTX 3090
arXiv:2609.28322v1 Announce Type: new Abstract: Benchmarking and routing platforms increasingly act as intermediaries connecting large language model providers with end-users. However, providers on th
arXiv:2609.24876v1 Announce Type: new Abstract: In multi-agent social settings, model reliability varies across relationships. Beyond inferring what others will do, an agent must calibrate how confide
arXiv:2609.12551v2 Announce Type: replace-cross Abstract: AI is beginning to make substantive contributions to LLM inference optimization. Existing AI optimizations are predominantly profiling-based.
arXiv:2609.25145v1 Announce Type: cross Abstract: Variational autoencoders (VAEs) offer an efficient approach to amortized Bayesian inference for inverse problems, but posterior accuracy can depend st
arXiv:2609.23219v1 Announce Type: new Abstract: Unobserved confounding is a fundamental challenge in causal inference from observational data. This article develops a mixture-learning perspective, vie
NVIDIA Confidential Computing (CC) secures large‑language‑model inference by providing encrypted virtual machines, GPUs, and NVLink, enabling processing of sensitive data in trusted hardware. Running
arXiv:2609.22587v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models commonly predict action chunks, limiting their ability to react to environmental changes during execution. Existing