Knowledge catalogue
arXiv:2607.26192v1 Announce Type: new Abstract: Input-dependent controller coefficients are often treated as evidence of dynamic inference or computational savings. This interpretation conflates three
arXiv:2607.22640v1 Announce Type: cross Abstract: Short-term environmental exposures have been linked to cognitive and behavioral outcomes, although many reported associations may reflect broader geog
arXiv:2607.23264v1 Announce Type: cross Abstract: Fine-grained, device-initiated communication lets persistent GPU kernels in distributed diffusion transformer (DiT) inference issue remote stores and
arXiv:2603.19139v2 Announce Type: replace Abstract: Learning systems must balance generalization across experiences with discrimination of task-relevant details. Effective learning therefore requires
Kimi K3 is now available on @digitalocean 's Serverless Inference! Developers can start building with our most capable model in minutes. .@Kimi_Moonshot K3 from Moonshot AI is now live on DigitalOcean
arXiv:2607.21591v1 Announce Type: new Abstract: Diffusion and flow-matching models dominate conditional image generation, yet inference-time scaling for these models is far less developed than for aut
arXiv:2607.19459v1 Announce Type: cross Abstract: Modeling galaxy-galaxy strong gravitational lenses to infer the brightness of the source galaxy and the mass distribution of the foreground galaxy is
arXiv:2607.13095v1 Announce Type: cross Abstract: We present a full-pipeline inference optimization for the MiMo-V2.5 model family, which combines Hybrid Sliding Window Attention (Hybrid SWA), sparse
The race to build the fastest AI infrastructure is reshaping the semiconductor industry, with inference speed emerging as the defining competitive dimension of the AI era. As AI model wars intensify a
arXiv:2607.04650v1 Announce Type: cross Abstract: Probabilistic inference in high-dimensional Bayesian networks is difficult because exact manipulation of the joint distribution scales exponentially w
arXiv:2607.04668v1 Announce Type: cross Abstract: On-device LLM decoding is a hard-barriered CPU-SIMD computation that wants every core for milliseconds per token, while the rest of the OS wants those
arXiv:2607.04819v1 Announce Type: new Abstract: Fully homomorphic encryption (FHE) enables computation on encrypted data, but practical encrypted Transformer inference is bottlenecked by the sequentia
arXiv:2607.03904v1 Announce Type: new Abstract: Pulsar timing arrays (PTAs) provide a unique window into nanohertz gravitational waves (GWs), but extracting astrophysical parameters from noisy, long-b
This article shares practical lessons and best practices from teams operating large-scale machine learning inference systems in production environments. It covers challenges and solutions related to m
arXiv:2603.17415v2 Announce Type: replace-cross Abstract: Image registration is an ill-posed dense vision task, where multiple solutions achieve similar loss values, motivating probabilistic inference
arXiv:2606.28529v1 Announce Type: cross Abstract: Embodied foundation models have recently been widely used to improve robot generalization and task success rates. Previous works apply lossy efficient
An interesting way to take Noam at his word in regards to always keeping a constant inference budget for any eval reporting - is that open models have a lot more dollar per token mileage than closed m
arXiv:2606.27286v1 Announce Type: new Abstract: Mechanistic epidemiological models are widely used to support infectious disease forecasting and public-health decision making. Bayesian calibration of
arXiv:2606.25432v1 Announce Type: cross Abstract: Inference efficiency is typically pursued by shrinking the model: distillation, pruning, quantization, and sparse routing each lower per-token cost wh
arXiv:2606.20658v1 Announce Type: cross Abstract: Planning under uncertainty requires agents to balance goal achievement with information gathering. Active inference addresses this through the Expecte
The next generation of inference needs purpose-built infrastructure. Together AI and 5C are deploying NVIDIA GB300 NVL72 systems with high-density compute, advanced cooling, and AI-optimized storage f
arXiv:2606.11357v1 Announce Type: cross Abstract: With the growing demand for on-device LLM inference, edge SoCs increasingly integrate NPUs to improve performance and energy efficiency under tight po
DeepSeek Inference Analysis Day 0 GB200 NVL72, Blackwell, AMD MI355X Huawei performance analysis Performance every day over time for the past 44 days DeepSeekV4 1.6T Day 0 to Day 43 Performance Over T
arXiv:2602.08733v2 Announce Type: replace Abstract: Ordinary differential equations (ODEs) are central to scientific modelling, but inferring their vector fields from noisy trajectories remains challe
arXiv:2606.06527v1 Announce Type: cross Abstract: Energy-efficient edge inference requires reducing arithmetic cost, memory traffic, and hardware overhead. This paper presents an ablation-focused stud
This blog has previously discussed FHE for ML inference in the post Enable fully homomorphic encryption with Amazon SageMaker endpoints for secure, real-time inferencing, but this post goes a little f
arXiv:2604.07472v2 Announce Type: replace Abstract: Serving large language model (LLM) inference in cloud environments requires jointly optimizing model selection, GPU provisioning, parallelism config
arXiv:2606.05042v1 Announce Type: cross Abstract: Marginal inference in discrete graphical models forces a choice between exactness and scalability: exact algorithms are intractable for high-treewidth
arXiv:2606.04324v1 Announce Type: new Abstract: One of the primary challenges in Bayesian inference on the parameters of a diffusion model from discrete observations is the unavailability of an analyt
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:2606.02011v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) rely on long reasoning traces, making inference expensive. While low-bit quantization reduces per-token decoding cost, we
arXiv:2603.19262v2 Announce Type: replace-cross Abstract: Large language models increasingly rely on inference-time procedures such as chain-of-thought reasoning, self-refinement, retrieval augmentati
arXiv:2605.29673v1 Announce Type: cross Abstract: Reconstruction-based inference assigns a class by comparing class-wise reconstruction residuals; Sparse Representation Classification (SRC) is a canon
arXiv:2605.28488v1 Announce Type: cross Abstract: We study inference in stochastic block models (SBMs) through the lens of optimal transport (OT). We first establish that maximum likelihood variationa
arXiv:2509.04632v2 Announce Type: replace-cross Abstract: Large collections of tabular data from data lakes, web tables and open data portals often originate from heterogeneous sources, leading to rep
arXiv:2605.27309v1 Announce Type: new Abstract: The widespread use of AI services has raised concerns for its environmental sustainability, towards which recent studies have identified carbon emission
arXiv:2502.06567v2 Announce Type: replace-cross Abstract: Quantizing machine learning models has demonstrated its effectiveness in lowering memory and inference costs while maintaining performance lev
NVIDIA's Blackwell GB200 NVL72 architecture achieved the fastest-ever results on the STAC-AI benchmark for financial LLM inference, delivering up to 3.2x single-GPU performance improvements over the p
NVIDIA Dynamo Snapshot introduces ModelExpress for 7x faster startup via checkpoint restore and weight streaming with NVIDIA NVLink and NIXL , enabling efficient model initialization for inference wor
arXiv:2510.05699v4 Announce Type: replace-cross Abstract: Membership inference attacks (MIAs) are widely used to assess the privacy risks associated with machine learning models. However, when these a
arXiv:2605.25004v1 Announce Type: cross Abstract: Inferring network-wide traffic states from sparse observations with high accuracy and trustworthy uncertainty quantification is essential for intellig
arXiv:2605.24391v1 Announce Type: cross Abstract: As the demand for deep learning grows, cost reduction through quantization has become essential for both training and inference. In 2022, the Open Com
arXiv:2605.25682v1 Announce Type: cross Abstract: Distributing Transformer inference across embedded edge devices can alleviate individual memory and compute constraints, yet practical benefits on rea
arXiv:2604.00499v2 Announce Type: replace Abstract: To schedule LLM inference, the extit{shortest job first} (SJF) principle is favorable by prioritizing requests with short output lengths to avoid he
arXiv:2601.22367v2 Announce Type: replace-cross Abstract: Generalized Bayesian Inference (GBI) tempers a loss with a temperature eta > 0 to mitigate overconfidence and improve robustness under model m
arXiv:2605.23057v1 Announce Type: cross Abstract: ModeSwitch-LLM is a lightweight request-boundary controller for improving single-GPU large language model inference efficiency by routing each request
arXiv:2511.09557v4 Announce Type: replace-cross Abstract: As large language models (LLMs) continue to grow in size, distributed inference has become increasingly important. Model-parallel strategies m
arXiv:2605.18597v1 Announce Type: new Abstract: Large language model (LLM) agents often rely on long sequences of low-level textual actions, resulting in large effective decision horizons and high inf
arXiv:2605.16786v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly needed for interactive mobile applications, but high-quality models exceed the limited DRAM available on s
arXiv:2406.14427v4 Announce Type: replace Abstract: A central challenge for intelligent agents in an uncertain world is striking the right balance between utility maximization and resource use, not on
arXiv:2605.17850v1 Announce Type: cross Abstract: iffusion-based generative models increasingly rely on inference-time guidance, adding a drift term or reweighting mixture of experts, to improve sampl
arXiv:2605.17842v1 Announce Type: new Abstract: Autoregressive language models execute Transformer layers sequentially, creating a latency bottleneck that is not removed by conventional tensor or pipe
arXiv:2504.07347v3 Announce Type: replace-cross Abstract: As demand for Large Language Models (LLMs) and AI agents grows rapidly, optimizing systems for efficient LLM inference becomes critical. While
arXiv:2605.15407v1 Announce Type: cross Abstract: We consider amortized Bayesian inference for nonlinear inverse problems in settings where only samples from the joint distribution of parameters and o
A milestone for Pearl Research Labs: our first major enterprise partnership is live with Together AI. @togethercompute’s inference platform is an ideal demonstration of @prlnet's value proposition — O
arXiv:2510.02952v3 Announce Type: replace Abstract: Inferring trajectories from longitudinal spatially-resolved omics data is fundamental to understanding the dynamics of structural and functional tis
Together AI and Pearl Research Labs announced a partnership aimed at lowering the cost of AI inference through collaborative research and development efforts. The partnership likely combines Together
arXiv:2602.04657v3 Announce Type: replace Abstract: Recently, reducing redundant visual tokens in vision-language models (VLMs) to accelerate VLM inference has emerged as a hot topic. However, most ex
U.K.-based artificial intelligence inference chip startup Fractile Ltd. said today it has closed on a 220 million Series B round of funding. The company was founded in 2022 by the Oxford University-tr
arXiv:2605.13496v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become increasingly prevalent in cloud-based platforms, propelled by the introduction of AI-based consumer and enter