Knowledge catalogue
arXiv:2605.25916v1 Announce Type: new Abstract: Federated edge learning (FEEL) has recently emerged as a promising paradigm for achieving edge intelligence (EI) via enabling collaborative model traini
arXiv:2605.25819v1 Announce Type: new Abstract: Membership inference attacks (MIAs) are popular methods for empirically assessing the leakage of sensitive information in the training data through mode
arXiv:2605.23971v1 Announce Type: cross Abstract: This work presents a physics-guided machine-learning framework for carbon monoxide concentration inference from experimentally measured resistance tra
The Information: Source: AI inference provider Baseten is in talks to raise 1B at a post-money valuation of 11B, up from 5B after its 300M Series E announced in January — AI startup Baseten has recent
arXiv:2605.25547v1 Announce Type: new Abstract: Existing embodied control research demonstrates remarkable performance improvements by scaling training data and model size. We instead explore inferenc
arXiv:2603.23565v2 Announce Type: replace-cross Abstract: Safe reinforcement learning (RL) is a standard paradigm for safety-critical decision making. However, real-world safety constraints can be com
arXiv:2605.23348v1 Announce Type: cross Abstract: AI power demand is growing at an unprecedented rate while power grids are often ailing and struggle to keep up. Grid expansion comes with high capital
Our inference stack, optimized for Blackwells, with a novel attention kernel and many new optimizations has started rolling out! It's already charting on Artificial Analysis, eg: #1 speed and latency
arXiv:2605.22237v1 Announce Type: cross Abstract: Fully homomorphic encryption (FHE) supports only additions and multiplications, so FHE-only neural-network inference typically replaces ReLU with poly
arXiv:2602.05873v2 Announce Type: replace Abstract: Bayesian (deep) neural networks (BNN) are often more attractive than the vanilla point-estimate deep learning in various aspects including uncertain
arXiv:2603.21610v2 Announce Type: replace Abstract: Compliance monitoring in rule-governed domains (tax administration, clinical protocol adherence, environmental regulation) faces three structural ob
arXiv:2605.21798v1 Announce Type: new Abstract: Neural processes amortize Gaussian process inference, replacing the exact O(n^3) posterior with a learned O(n) map from context sets to predictive distr
This article describes techniques for using prompt caching to improve the inference speed and efficiency of open-source large language models when deployed on Databricks' platform. Prompt caching redu
Cheng Ting-Fang / Nikkei Asia: AMD CEO Lisa Su projects the CPU market will grow over 35% annually through 2031, up from 3% to 4% historically, driven by AI inference and agentic AI demand — TAIPEI —
arXiv:2605.22373v1 Announce Type: cross Abstract: Safety classifiers are essential safeguards within generative AI systems, filtering harmful content or identifying at-risk users when interacting with
arXiv:2605.20802v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) exploit event-driven and addition-only computation to substantially improve efficiency for intelligent computation. A k
MTP means Multi Token Prediction. It's a speculative decoding technique that can result in large inference speedups in many cases. 1. Update to LM Studio 0.4.14 2. Download a model that supports MTP l
arXiv:2605.22044v1 Announce Type: new Abstract: Accurate localization of myocardial infarction is essential for risk stratification. While LGE-MRI remains the gold standard, it is resource-intensive.
arXiv:2605.22206v1 Announce Type: cross Abstract: The Thousand Brains Theory (TBT) and its open-source Monty framework model object recognition through sensorimotor inference -- identifying objects by
arXiv:2605.20726v1 Announce Type: cross Abstract: Modern applications of conformal inference to multiple testing problems, such as outlier detection and candidate selection, often involve selecting te
arXiv:2605.21253v1 Announce Type: cross Abstract: Compositional score-based approaches to simulation-based inference (SBI) approximate the posterior over a shared parameter given n independent observa
LLMs are stateless (every time you reply to an LLM, you re-inject the entire conversation to a fresh inference) the purpose of memory is to provide continuity (in games we'd call it a 'persistent worl
arXiv:2605.19218v1 Announce Type: cross Abstract: Vision-Language Models suffer severe KV cache pressure at inference, as a single image often encodes into thousands of tokens. Most existing methods e
arXiv:2602.18718v2 Announce Type: replace-cross Abstract: For approximating a target distribution given only its unnormalized log-density, stochastic gradient-based variational inference (VI) algorith
arXiv:2605.20179v1 Announce Type: new Abstract: Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive (AR) models, offering better hardware utilization an
arXiv:2605.17609v1 Announce Type: new Abstract: Many inference-time language-model pipelines combine a cheap reward signal with an expensive verifier, such as exact answer checking in mathematical rea
This article presents benchmarking results for AI coding agents evaluated at scale, likely comparing performance metrics such as code generation accuracy, execution success rates, and inference effici
arXiv:2605.18374v1 Announce Type: cross Abstract: Large language models (LLMs) typically approach combinatorial optimization as an inference-time procedure, solving each instance separately through sa
arXiv:2506.23287v3 Announce Type: replace Abstract: In single-cell research, tracing and analyzing high-throughput single-cell differentiation trajectories is crucial for understanding biological proc
arXiv:2603.29167v2 Announce Type: replace Abstract: We study a systems-level visual inference problem: using an expensive privileged modality during training while preserving a fixed-cost, single-moda
arXiv:2603.14371v2 Announce Type: replace-cross Abstract: Embodied AI agents increasingly require parallel execution of multiple tasks, such as manipulation, conversation, and memory construction, fro
arXiv:2605.16360v1 Announce Type: cross Abstract: Efficient long-context inference in Large Language Models (LLMs) is severely constrained by the Key-Value (KV) cache memory wall, yet existing pruning
Anna Tong / Forbes: Sources: Zyphra, which trains and runs inference for its open-weight models on AMD hardware, is raising a 500M Series B at a valuation of at least 5B — The Series B round, which ch
arXiv:2605.16387v1 Announce Type: cross Abstract: Online Surgical Phase Recognition (SPR) models can reach high frame-wise accuracy, yet their predictions often lack temporal stability, fragmenting wo
arXiv:2605.17170v1 Announce Type: new Abstract: Agentic workloads have emerged as a major workload for LLM inference. They differ significantly from chat-only workloads, requiring long-context process
⚡️After weeks of hard work, we're thrilled to fully open-source HY World 2.0 today -- full inference code and all models! Build, explore, and create your own interactive worlds with us.👇 https://githu
arXiv:2603.01290v3 Announce Type: replace Abstract: The 2026 Formula 1 technical regulations introduce a fundamental change to energy strategy: under a 50/50 internal combustion engine / battery power
arXiv:2504.11320v3 Announce Type: replace-cross Abstract: Large language models now serve millions of users daily, with providers incurring costs exceeding $700,000 per day. Each request requires toke
Teams like @modal are already using Devin Auto-Triage for incidents on their inference team. “Devin Automations feels like a step forward from other auto-triage tools we’ve tried. It monitors our chan
Heading to hashtag#MLSys2026? Come unwind with the Together AI team at Inference After Dark. Drinks, bites, shuffleboard, and a room full of researchers and AI-native builders. 🟠 Tuesday, May 19 🟠 7:3
arXiv:2605.15100v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable abilities in reasoning. However, maximizing their potential through inference-time scaling fac
arXiv:2605.14249v1 Announce Type: new Abstract: We present EnergyLens, an end-to-end framework for energy-aware large language model (LLM) inference optimization. As LLMs scale, predicting and reducin
arXiv:2605.13915v1 Announce Type: cross Abstract: Quantization is essential for efficient large language model (LLM) inference, yet the dequantization step-converting low-bit weights back to high-prec
arXiv:2511.16964v2 Announce Type: replace-cross Abstract: Maximizing performance on available GPU hardware is an ongoing challenge for modern AI inference systems. Traditional approaches include writi
Pearl generates proofs from matrix multiplications that already happen during training and inference computations. Those proofs help secure Pearl Network, and the future value of Pearl emissions helps
arXiv:2605.14142v1 Announce Type: cross Abstract: Integration against a probability distribution given its unnormalized density is a central task in Bayesian inference and other fields. We introduce n
arXiv:2605.14844v1 Announce Type: cross Abstract: We introduce XFP, a dynamic weight quantizer for LLM inference that inverts the conventional workflow: the operator specifies reconstruction quality f
arXiv:2508.14302v2 Announce Type: replace-cross Abstract: Inference-time sparsification is a promising path to deploy large language models (LLMs) on resource-constrained devices, yet existing trainin
great agents need great infrastructure. proud to be @LangChain's Deep Agents Inference Partner at Interrupt 2026 in SF. great to spend time with builders at our day 1 happy hour. excited for day 2 tod
arXiv:2605.12765v1 Announce Type: new Abstract: Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety. Machine unlearning
arXiv:2605.12653v1 Announce Type: cross Abstract: Reinforcement learning agents for portfolio management are typically trained and deployed as static policies, with no mechanism for using price foreca
Training a diffusion LLM from scratch is challenging, and diffusion inference advantages don't show up at training. So we convert instead. Building on the TiDAR recipe, we take ZAYA1-8B-base and run d
arXiv:2605.11335v1 Announce Type: cross Abstract: Layerwise offloading reduces the GPU memory footprint of large diffusion transformer (DiT) inference by prefetching upcoming layers from host memory,
arXiv:2605.11537v1 Announce Type: new Abstract: The Mixture of Experts (MoE) architecture has become a fundamental building block in state-of-the-art large language models (LLMs), improving domain-spe
Dutch artificial intelligence infrastructure giant Nebius Group N.V. said today it’s recruiting the core engineering team from AI orchestration software firm Clarifai Inc. in an effort to boost its ma
Robbie Whelan / Wall Street Journal: UK chip startup Fractile raised a $220M Series B led by Factorial Funds, Accel and Founders Fund to make specialized logic and memory chips for inference — Factori
arXiv:2605.11334v1 Announce Type: cross Abstract: LLM-as-Judge systems are widely deployed for automated evaluation, yet practitioners lack reliable methods to know when a judge's verdict should be tr
What we find most useful about TST is the decoupling. The training-time efficiency is fully separated from the inference-time architecture, which makes TST a clean addition on top of other pretraining
arXiv:2603.21901v2 Announce Type: replace Abstract: Video subtitle removal aims to distinguish text overlays from background content while preserving temporal coherence. Existing diffusion-based metho
arXiv:2512.00920v4 Announce Type: replace Abstract: Reliable reward models (RMs) are critical for ensuring the safe alignment of large language models (LLMs). However, current RM evaluation methods fo