Knowledge catalogue
arXiv:2510.18245v3 Announce Type: replace-cross Abstract: Scaling the number of parameters and the size of training data has proven to be an effective strategy for improving large language model (LLM)
arXiv:2605.11581v1 Announce Type: new Abstract: When large language models (LLMs) serve real-time inference in commercial online advertising systems, end-to-end latency must be strictly bounded to the
arXiv:2605.12471v1 Announce Type: cross Abstract: We introduce KV-Fold, a simple, training-free long-context inference protocol that treats the key-value (KV) cache as the accumulator in a left fold o
As companies move from testing AI to broader adoption, the biggest challenge is building scalable AI inference systems that perform without breaking the budget. The next wave of AI won’t be won on raw
arXiv:2605.11854v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive language models, offering stronger global awareness
arXiv:2509.14234v3 Announce Type: replace Abstract: Where do learning signals come from when there is no ground truth in post-training? We show that inference compute itself can serve as supervision.
arXiv:2510.23074v2 Announce Type: replace-cross Abstract: We propose Fast-MIA (https://github.com/Nikkei/fast-mia), a Python library for efficiently evaluating membership inference attacks (MIA) again
arXiv:2605.09839v1 Announce Type: cross Abstract: We introduce the Free Energy Manifold (FEM), a score-trained conditional energy model specialized for inference in hybrid Bayesian networks with discr
arXiv:2605.08343v1 Announce Type: new Abstract: Institutions may benefit from collaborative inference on time-series data. In settings where privacy is necessary, multi-party computation (MPC) is a st
arXiv:2605.09931v1 Announce Type: cross Abstract: Tool-integrated reasoning (TIR) enables large language models (LLMs) to enhance their capabilities by interacting with external tools, such as code in
arXiv:2605.08128v1 Announce Type: cross Abstract: Gene Regulatory Network (GRN) inference is essential for understanding complex cellular mechanisms, rendered tractable through single-cell transcripto
arXiv:2605.10934v1 Announce Type: cross Abstract: Modelling extreme events and heavy-tailed phenomena is central to building reliable predictive systems in domains such as finance, climate science, an
arXiv:2602.01621v3 Announce Type: replace-cross Abstract: Homomorphic encryption (HE) is a prominent framework for privacy-preserving machine learning, enabling inference directly on encrypted data. H
For browser-use AI agents, every task is dozens of model calls in a tight loop. The inference layer isn’t background infrastructure. It’s what the product runs on. @yutori_ai runs Scouts, Delegate, an
arXiv:2605.07456v1 Announce Type: new Abstract: Inference-time controllable generation is essential for real-world applications of unconditional diffusion models. However, most existing techniques foc
arXiv:2605.07972v1 Announce Type: cross Abstract: Neural posterior estimation has emerged as a powerful tool for amortized inference, with growing adoption across scientific and applied domains. In ma
arXiv:2605.06951v1 Announce Type: new Abstract: Constraint inference is widely considered essential to align reinforcement learning agents with safety boundaries and operational guidelines by observin
arXiv:2605.07661v1 Announce Type: cross Abstract: Diffusion models achieve strong generation quality, diversity, and distribution coverage, but their performance often comes with expensive inference.
arXiv:2511.03475v4 Announce Type: replace Abstract: AI applications increasingly depend on long-context inference, where LLMs consume substantial context to support stronger reasoning. Common examples
arXiv:2605.00955v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) equips large language models (LLMs) with external evidence by retrieving documents at inference time, but it also
arXiv:2601.02241v5 Announce Type: replace-cross Abstract: Graphs arise across diverse domains, from biology and chemistry to social and information networks, as well as in transportation and logistics
arXiv:2605.02323v1 Announce Type: new Abstract: Compositional inference - the decomposition of observations into an unknown number of latent components - is central to perception and scientific data a
Today, Amazon SageMaker AI introduces capacity aware instance pool for new and existing inference endpoints. You define a prioritized list of instance types, and SageMaker AI automatically works throu
arXiv:2605.00005v1 Announce Type: new Abstract: The increasing deployment of deep neural networks (DNNs) in cyber-physical systems (CPS) enhances perception fidelity, but imposes substantial computati
arXiv:2506.00166v2 Announce Type: replace-cross Abstract: Existing paradigms for ensuring AI safety, such as guardrail models and alignment training, often compromise either inference efficiency or de
DigitalOcean outlines its AI-native cloud infrastructure designed to support the inference phase of AI model deployment, emphasizing tools and services that enable businesses to run and scale AI model
arXiv:2604.27307v1 Announce Type: cross Abstract: Causal inference is essential for data-driven decision-making, as it aims to uncover causal relationships from observational data. However, identifyin
arXiv:2602.19179v2 Announce Type: replace Abstract: Gaussian inference on smooth manifolds is central to robotics, but exact marginalization and conditioning are generally non-Gaussian and geometry-de
arXiv:2603.06635v2 Announce Type: replace Abstract: Recent progress in language modeling has expanded the range of tasks that can be approached through natural language interfaces, including problems
arXiv:2604.23904v1 Announce Type: cross Abstract: Synthetic data offers a promising tool for privacy-preserving data release, augmentation, and simulation, but its use in causal inference requires pre
arXiv:2503.10666v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have become widely used across various domains spanning search engines, code generation, and text creation. Howev
arXiv:2506.04118v3 Announce Type: replace Abstract: We propose Guided Speculative Inference (GSI), a novel algorithm for efficient reward-guided decoding in large language models. GSI combines soft be
arXiv:2505.02922v3 Announce Type: replace Abstract: Recent large language models (LLMs) are rapidly extending their context windows, yet inference throughput lags due to increasing GPU memory and band
arXiv:2508.09603v2 Announce Type: replace Abstract: Membership inference attacks serves as useful tool for fair use of language models, such as detecting potential copyright infringement and auditing
arXiv:2604.22575v1 Announce Type: new Abstract: Scaling context length is reshaping large-model development, yet full-attention Transformers suffer from prohibitive computation and inference bottlenec
arXiv:2510.18914v4 Announce Type: replace-cross Abstract: Large language models often display undesirable behaviors embedded in their internal representations, undermining fairness, inconsistency drif
At 30 trillion tokens a day, we're the largest inference provider outside the frontier labs' own APIs. We're hiring. Come build the infrastructure behind the top AI workloads: https://fireworks.ai/car
arXiv:2604.19757v1 Announce Type: cross Abstract: This paper presents a transparent screening framework for estimating inference and training impacts of current large language models under limited obs
arXiv:2604.19351v1 Announce Type: new Abstract: The quadratic computational complexity of the standard attention mechanism constitutes a fundamental bottleneck for large language models in long-contex
arXiv:2510.09477v2 Announce Type: replace-cross Abstract: Set-based transformer models for amortized probabilistic inference and meta-learning, such as neural processes, prior-fitted networks, and tab
arXiv:2604.19623v1 Announce Type: cross Abstract: Edge-cloud hybrid inference offloads difficult inputs to a powerful remote model, but the uplink channel imposes hard per-request constraints on the n
arXiv:2604.18820v1 Announce Type: cross Abstract: Recovering latent structure from count data has received considerable attention in network inference, particularly when one seeks both cross-group int
arXiv:2510.12916v2 Announce Type: replace-cross Abstract: Systems of interacting continuous-time Markov chains are a powerful model class, but inference is typically intractable in high dimensional se
arXiv:2604.16763v1 Announce Type: new Abstract: Causal inference from electronic health records (EHR) is fundamentally limited by unmeasured confounding: critical clinical states such as frailty, goal
arXiv:2604.16957v1 Announce Type: new Abstract: We present Open-TQ-Metal, the first implementation of fused compressed-domain attention on Apple Silicon, enabling 128K-context inference for Llama 3.1
arXiv:2604.16834v1 Announce Type: cross Abstract: Privacy-preserving machine learning (PPML) has become increasingly important in applications where sensitive data must remain confidential. Homomorphi
arXiv:2510.21783v2 Announce Type: replace-cross Abstract: Diffusion models have demonstrated powerful performance in generating high-quality images. A typical example is text-to-image generator like S
arXiv:2604.15409v1 Announce Type: cross Abstract: KV caching is a ubiquitous optimization in autoregressive transformer inference, long presumed to be numerically equivalent to cache-free computation.
Fireworks AI published a compilation of insights on achieving training-inference parity in Mixture of Experts (MoE) models, addressing fundamental challenges in aligning model behavior between trainin
arXiv:2601.07667v2 Announce Type: replace Abstract: Due to the prevalence of large language models (LLMs), key-value (KV) cache reduction for LLM inference has received remarkable attention. Among num
arXiv:2604.14193v1 Announce Type: new Abstract: Human 3D vision involves two distinct stages: an Experience Module, where stereo depth is extracted relative to fixation, and an Inference Module, where
arXiv:2604.12737v1 Announce Type: cross Abstract: While Federated Learning (FL) mitigates direct data exposure, the resulting trained models remain susceptible to membership inference attacks (MIAs).
This post explores how Amazon SageMaker HyperPod provides a comprehensive solution for inference workloads. We walk you through the platform’s key capabilities for dynamic scaling, simplified deployme
arXiv:2602.17375v2 Announce Type: replace Abstract: We cast episodic Markov decision process (MDP) planning as Bayesian inference over policies. A policy is treated as the latent variable and is assig
arXiv:2511.03636v2 Announce Type: replace-cross Abstract: We perform a simulation-based forecasting analysis to compare the cosmological constraining power of higher-order summary statistics of the la
arXiv:2604.09681v1 Announce Type: cross Abstract: With the rapid growth of large-scale video analytics applications, edge-cloud collaborative systems have become the dominant paradigm for real-time in
arXiv:2412.15803v2 Announce Type: replace-cross Abstract: Advancements in large language models (LLMs) have unlocked remarkable capabilities. While deploying these models typically requires server-gra
Nvidia published DWDP (Distributed Weight-Data Parallelism), a new inference parallelism strategy focused on prefill. It sounds slightly insane until you remember the target machine is GB200 NVL72. Th
arXiv:2606.14977v2 Announce Type: replace-cross Abstract: This paper provides identification results to characterize a fairness-accuracy (FA) frontier, and statistical inference tools to test hypothes
arXiv:2610.20796v1 Announce Type: cross Abstract: Health-misinformation analysis presents a dual challenge: misleading claims can affect public well-being, while systems designed to detect them may ex