Knowledge catalogue
Catch up on July and August in Microsoft Foundry: stable Hosted Agent and Toolbox SDK paths, Claude tools on Azure-hosted deployments, Model Router updates, local inference improvements, and the SDK m
arXiv:2609.07002v1 Announce Type: new Abstract: Generalizable and robust dexterous in-hand manipulation requires a policy to infer object pose, geometry, contact, and potential slip from partial and n
Managed MLflow on Amazon SageMaker AI now syncs richer model metadata (training metrics, evaluation results, inference specs, and lineage) into the SageMaker AI Model Registry, with lifecycle stage pr
Hello LocalLLaMA Fam! I built this project because I, like many of us here, enjoy local AI and have a nice setup, but still find myself reaching for Cloud-based AI due to their convenience. My models
GPT-6 Astra from OpenAI is now generally available on Amazon Bedrock. It brings deeper reasoning and sharper judgment to your most demanding tasks, running on the Amazon Bedrock inference engine built
arXiv:2609.04695v1 Announce Type: cross Abstract: Large-volume neutrino telescopes infer neutrino properties from Cherenkov light, but simulating the transport of billions of photons through highly sc
arXiv:2602.03102v2 Announce Type: replace Abstract: Many strong decoding methods for text generation follow a sample-and-rerank paradigm: they draw multiple candidates, score each under a utility (rew
Fascinating paper from Anthropic and colleagues. They study whether models can tell when they are being tested. It turns out that capable models can tell when they are being tested rather than deploye
arXiv:2609.04592v1 Announce Type: new Abstract: Intelligent extended reality (XR) systems increasingly use eye and head tracking to infer user intent, task, and attention, but the same signals can als
Krea 2 Turbo — 4-Step Distillation LoRA Full details and to download - HF Repo: https://huggingface.co/lvladikov/Krea2-Turbo-Distill-4step-LoRA https://preview.redd.it/9p2rjwh3y3oh1.jpg?width=3072&for
arXiv:2609.04511v1 Announce Type: new Abstract: Latent entity extraction (LEE) tackles the challenge of identifying implicit, contextually inferred entities within free text-an area where traditional
arXiv:2609.04620v1 Announce Type: new Abstract: Personalized autonomous packing requires robots to account for resident preferences that cannot be inferred from scene geometry alone. Expert teleoperat
arXiv:2609.05235v1 Announce Type: cross Abstract: Cryptocurrency markets exhibit extreme volatility and non-stationary dynamics that challenge conventional forecasting methods. Although Large Language
arXiv:2609.04710v1 Announce Type: cross Abstract: Inferring cellular dynamics from unpaired single-cell snapshots requires modeling both state transitions and population growth or death. Unbalanced dy
arXiv:2609.05282v1 Announce Type: new Abstract: Reliable robot-to-human handover requires the robot to infer when the person is ready to receive the object, and release it safely, comfortably, and at
arXiv:2510.11839v3 Announce Type: replace Abstract: Time series are ubiquitous in many applications that involve forecasting, classification and causal inference tasks, such as healthcare, finance, au
Hello, I'm a bit obsessed with cache management on local LLMs. For the last few days I've been working on cache management on vLLM with my 2x DGX Spark and DeepSeek v4 Flash 0731. I felt something was
I've been running Qwen3.8-27B as a local inference server for a production content intelligence pipeline (HVAC industry stuff, lots of long-context retrieval and structured extraction). I have been wa
arXiv:2609.04018v1 Announce Type: new Abstract: Quantile treatment effects (QTEs) measure the effect of a treatment on the distribution of an outcome, and their estimation at extreme quantile levels i
The era of AI inference has arrived. Imagine a healthcare system analyzing millions of data points in real time to accelerate life-saving medical research, or an intelligent assistant instantly resolv
arXiv:2609.02890v1 Announce Type: new Abstract: A personalized language agent must convert a user's interaction history into behavior on each new request at inference time. Two strategies dominate. Re
Hey everyone, been a while! https://huggingface.co/TheDrummer/Artemis-31B-v1.1 https://huggingface.co/TheDrummer/Artemis-31B-v1 A few months ago, Gemma graced us with models that served as a much need
arXiv:2609.04031v1 Announce Type: new Abstract: Video diffusion models (VDMs) have achieved impressive progress in text-to-video generation, but their high memory and computational costs hinder practi
arXiv:2609.03423v1 Announce Type: new Abstract: Full-duplex voice agents must continuously decide when to listen, backchannel, interrupt, handle speech overlaps, take the floor, and yield. Existing be
arXiv:2609.03080v1 Announce Type: new Abstract: Segmenting a new biomedical dataset usually means a domain-specific model trained on substantial annotation, or a foundation model steered at inference
arXiv:2609.03494v1 Announce Type: new Abstract: Long-output reasoning has made the key--value (KV) cache a critical memory bottleneck for efficient LLM serving. Existing KV compression methods usually
arXiv:2604.05460v2 Announce Type: replace-cross Abstract: Large language model (LLM) evaluation platforms increasingly rely on pairwise human judgments. These data are noisy, sparse, and non-uniform,
arXiv:2609.02897v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by drafting candidate tokens and verifying them in parallel. Tree-attention drafters such as EAGLE-3 are
arXiv:2609.03379v1 Announce Type: new Abstract: Repeating a small block of middle layers increases a language model's effective inference depth without adding parameters or generating extra tokens, an
arXiv:2609.03236v1 Announce Type: new Abstract: Tool-using LLM agents spend wall-clock time not only on model inference but also in serial action--observation turns, where each tool call, environment
arXiv:2609.04071v1 Announce Type: cross Abstract: Pathology foundation models improve transferable representation learning for histopathology, but recent gains often rely on encoders with hundreds of
The preview releases of Solaris and GWM 2 Worlds this week are just a glimpse of what happens when video world models are scaled significantly and paired with real-time inference. It's a real-time sim
arXiv:2609.04010v1 Announce Type: new Abstract: Large Language Models (LLMs) owe much of their success to next-token prediction (NTP), but their autoregressive (AR) structure requires slow, sequential
arXiv:2609.03880v1 Announce Type: new Abstract: We introduce Xiaomi-TabLDM, a tabular large data foundation model for classification and regression via in-context learning, which delivers superior pre
Github link: https://github.com/thatblend/LLMPSP I wanted to see what the PSP can theoretically handle and I got my answer - a 90M model is about the max it can do without atrocious inference speeds.
arXiv:2609.02315v1 Announce Type: cross Abstract: A single sentence often expresses multiple valid relational triplets, which makes Open Information Extraction (OpenIE) fundamentally a multi-output ta
arXiv:2609.01888v1 Announce Type: new Abstract: Recent inference-time hallucination mitigation methods for large vision-language models (LVLMs) report strong gains on hallucination benchmarks. However
arXiv:2609.01691v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used to make decisions from visual inputs. We introduce FAIRLENS, a benchmark and evaluation framework fo
arXiv:2607.15600v2 Announce Type: replace Abstract: Monocular depth foundation models have demonstrated remarkable generalization capabilities across diverse environments. However, they continue to st
arXiv:2609.02251v1 Announce Type: new Abstract: Handwriting trajectory recovery aims to infer the dynamic writing process hidden behind a static handwritten image. Since offline handwriting preserves
arXiv:2609.01807v1 Announce Type: cross Abstract: Large language models (LLMs) achieve state-of-the-art generative ranking quality, but the ranking they produce must be decoded, and autoregressive dec
arXiv:2609.02138v1 Announce Type: cross Abstract: Stochastic gradient Markov chain Monte Carlo (SGMCMC) methods enable scalable Bayesian inference, but their performance depends strongly on hyperparam
arXiv:2609.01772v1 Announce Type: new Abstract: Meme understanding goes beyond recognizing visual content or literal text; it requires implicit cultural knowledge and pragmatic inference that most vis
arXiv:2609.01662v1 Announce Type: cross Abstract: For embodied systems, predictive agreement alone does not determine whether evidence warrants action; evidential origin matters. Repeated inference ov
Nvidia is announcing its new Personal AI Router (PAIR), a free tool that syncs up your home computers for tackling local AI inference tasks with tools like Ollama and LM Studio. Let's get the obvious
arXiv:2609.02140v1 Announce Type: cross Abstract: Encrypted traffic classification infers semantics beyond the flow record from transport-layer observables, and supervised training rests on labels tha
arXiv:2609.00686v1 Announce Type: cross Abstract: Local learning methods offer an alternative to end-to-end backpropagation, but their unstructured local objectives can produce weak feature learning i
arXiv:2609.00274v1 Announce Type: new Abstract: Two-sided service marketplaces are moving from deterministic request-form intake to AI-native probabilistic matching, enabled by large language models (
AI factory deployment is becoming a workload-sizing exercise rather than a custom infrastructure project. Enterprises need infrastructure spanning edge inference and large-model training. Broadcom Inc
arXiv:2609.01195v1 Announce Type: new Abstract: Entity matching (EM) requires fine-grained contextual understanding and domain knowledge. Recent work shows that large language models (LLMs) can serve
arXiv:2609.00413v1 Announce Type: new Abstract: Chain of thought prompting improves complex reasoning, but its long intermediate traces create substantial inference cost and hinder practical deploymen
arXiv:2609.01449v1 Announce Type: new Abstract: Diffusion models and recursive reasoners are both iterative, but they carry information across iterations differently. We add a persistent hidden state
arXiv:2609.00653v1 Announce Type: cross Abstract: Electroencephalography (EEG) is a non-invasive technique for measuring neural activity and has been widely used in neuroscience applications. Recent a
arXiv:2609.01274v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves language-model reasoning, but how these gains relate to inference-time decoding and searc
arXiv:2609.00066v1 Announce Type: cross Abstract: NVFP4 is an efficient microscaling format for low-bit inference, but activation outliers can still degrade quantization accuracy within NVFP4 blocks.
arXiv:2609.01273v1 Announce Type: new Abstract: Synthetic data has become a common component of machine learning research. While widely adopted, its use in privacy-sensitive contexts has quietly shift
arXiv:2609.00796v1 Announce Type: new Abstract: As one of the most critical challenges in large language models, contextual faithfulness directly determines their reliability in knowledge-intensive ap
arXiv:2609.01279v1 Announce Type: cross Abstract: Emotion is expressed in text along a wide spectrum, from surface lexical cues to inferences entangled with content. Most layer-wise analyses of emotio
arXiv:2603.02974v2 Announce Type: replace Abstract: DINO models provide rich patch-level representations that have recently enabled strong performance in unsupervised anomaly detection (UAD). Most exi
arXiv:2609.00921v1 Announce Type: new Abstract: Personalized Large Language Models (PLLMs) aim to tailor responses to individual users, where a central challenge is preference reasoning: inferring que