Knowledge catalogue
Provisioned Throughput gives you reserved inference capacity for frontier open models like MiniMax M3 and GLM-5.2. Token-based pricing, a 99% uptime SLA, and up to 90% lower cost than proprietary APIs
Together AI announced provisioned throughput capabilities, a feature that allows users to reserve dedicated model inference capacity at predictable costs. This offering enables organizations to optimi
This is a big update that I’m excited to finally share. We launched our first dev platform for AI media in 2020, offering a simple API and a diverse set of models. Back then, we built a powerful SDK a
arXiv:2607.03256v1 Announce Type: new Abstract: Few-step distilled diffusion students cut text-to-image inference from ~50 to 1-8 network evaluations, but the quality gap is usually summarised by a si
arXiv:2204.02803v2 Announce Type: replace-cross Abstract: Sign language recognition from monocular video or 2D pose sequences is challenging, both because 3D information must be inferred from 2D obser
arXiv:2607.04224v1 Announce Type: cross Abstract: AI-RAN aims to unify artificial intelligence and radio access network workloads on a shared compute substrate. While this paradigm has so far been dem
arXiv:2607.03162v1 Announce Type: new Abstract: LLM-powered agents struggle with personalization when users issue raw, underspecified queries. In this setting, agents must infer latent intent, extract
arXiv:2601.07475v2 Announce Type: replace-cross Abstract: The emergence of fine-grained numerical formats like NVFP4 presents new opportunities for efficient Large Language Model (LLM) inference. Howe
Release b9895 of llama.cpp includes a fix for speculative inference out-of-bounds read in ngram-map on prompt shrink, with ~2x performance gains in PP_Speed for FP32, Q4_0 and Q8_0 models. The release
arXiv:2607.03453v1 Announce Type: cross Abstract: Inference-time alignment methods, such as Best-of-N, offer a flexible alternative to training-based alignment by using reward models to select high-qu
arXiv:2607.04619v1 Announce Type: cross Abstract: Modern automated audio captioning systems pair a frozen audio encoder with a large language model (LLM) via a trainable projector, incurring the encod
arXiv:2607.04513v1 Announce Type: cross Abstract: Flow matching is a powerful tool for generative modeling, but emerging applications in robotics, planning, and physics require inference-time constrai
arXiv:2607.04809v1 Announce Type: cross Abstract: Tabular Foundation Models (TFMs) have demonstrated strong empirical performance as black-box inference engines through in-context learning. However, t
arXiv:2511.13649v5 Announce Type: replace Abstract: Distribution Matching Distillation (DMD) facilitates efficient inference by distilling multi-step diffusion models into few-step variants. Concurren
arXiv:2607.05147v1 Announce Type: new Abstract: Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification. While recent parallel dra
Chinese AI startup DeepSeek is developing its own inference chips to reduce Nvidia dependence and break U.S. export controls, as China moves to protect its AI ecosystem. DeepSeek has been quietly deve
arXiv:2607.03787v1 Announce Type: new Abstract: Accurately modeling biomolecular interactions is a central bottleneck in biology and therapeutic discovery. Here, we introduce Open Drug Discovery Engin
arXiv:2607.04241v1 Announce Type: cross Abstract: Plasma disruption is a critical threat to tokamak safety. Existing data-driven predictors mainly rely on time-series diagnostic signals, while visible
arXiv:2607.04884v1 Announce Type: new Abstract: We present HunyuanOCR-1.5, a lightweight end-to-end OCR-specialized vision-language model. HunyuanOCR unifies document parsing, text spotting, informati
arXiv:2607.04647v1 Announce Type: cross Abstract: Scalable Bayesian inference for generalized linear mixed models (GLMMs) provides uncertainty-aware analysis of correlated longitudinal data, but exist
arXiv:2607.02549v1 Announce Type: new Abstract: Many manipulation tasks require reasoning about free-space affordances: discovering volumes where an extended rigid tool can safely navigate, complement
arXiv:2607.02703v1 Announce Type: cross Abstract: In this paper, we describe LLMoxie, an institutional AI platform whose three-tiered architecture supports multi-cloud and on-premise inference, a Lite
arXiv:2211.10872v2 Announce Type: replace Abstract: Open-set recognition refers to the problem in which classes that were not seen during training appear at inference time. This requires the ability t
arXiv:2607.02881v1 Announce Type: new Abstract: Long-horizon behavior prediction aims to infer a user's next action based on a lengthy historical sequence, playing a crucial role in artificial intelli
arXiv:2511.05730v2 Announce Type: replace Abstract: In this paper, a learning framework is introduced which incorporates principles of probabilistic inference, variational optimization, and geometry-p
arXiv:2607.05199v1 Announce Type: new Abstract: Physics reasoning fails structurally in small language models: an error at any step propagates forward, corrupting every inference that follows. Limited
arXiv:2607.05364v1 Announce Type: cross Abstract: Modern autoregressive ASR systems can emit timestamps as decoded tokens, enabling timestamped transcription without frame-level aligners or inference-
arXiv:2607.02983v1 Announce Type: new Abstract: Recent reasoning-centric Large Language Models (LLMs) have made significant strides, yet they predominantly operate on a passive-inference pattern that
arXiv:2607.03165v1 Announce Type: new Abstract: Brain decoding aims to uncover neural mechanisms by inferring stimulus-related representations from brain signals. In fMRI studies, this is typically ac
arXiv:2607.03058v1 Announce Type: new Abstract: Post-refinement can improve colonoscopy segmentation after host inference, but many designs still rely on extra correction heads or multi-stage pipeline
arXiv:2607.03809v1 Announce Type: new Abstract: Normalising flows provide a powerful variational family for approximate inference, yet individual architectures often fail to generalise across heteroge
arXiv:2607.03089v1 Announce Type: cross Abstract: HAR is increasingly expected to run continuously on edge devices, yet recent LLM-based methods remain hard to deploy: raw sensor prompts are long, clo
arXiv:2607.04945v1 Announce Type: new Abstract: LLMs enable the integration of external conceptual resources at inference time, creating new opportunities for detecting ideologically and historically
b9881 is a release of llama.cpp, an LLM inference tool written in C/C++. This release likely includes bug fixes, performance improvements, and platform support enhancements for running large language
B9885 is a build-tagged release of llama.cpp, an open-source C/C++ inference engine for running large language models locally. The project does not use traditional semantic versions; instead it ships
// ReContext // Models now support 128K context windows and still fail to use evidence that is already in the prompt. Where is the gap? New paper introduces ReContext, a training-free inference harnes
In this post, we walk through how to get started with MiniMax models on Amazon Bedrock, including the capabilities supported by these models, the service tiers available, how on-demand inference scale
In this post, you learn how to use the new MLflow integration with Amazon SageMaker AI optimized inference recommendation jobs and Amazon SageMaker AI benchmark jobs to automatically stream experiment
llama.cpp is a tool for LLM inference in C/C++ and b9864 is a release version tag from the ggml-org/llama.cpp GitHub repository. Based on the release numbering pattern and project scope, this release
Don't forget, we'll be in Paris for @RaiseSummit. Will we see you there? Going to be in Paris for @RaiseSummit? Join us and @nvidia to hear from leaders at both companies on the future of AI inference
arXiv:2603.18315v2 Announce Type: replace-cross Abstract: Traditional reinforcement learning (RL) methods rely on manually engineered rewards or sparse collision signals, which fail to capture the ric
arXiv:2607.01729v1 Announce Type: new Abstract: Deep learning models for speech classification are vulnerable to backdoor attacks, where malicious triggers cause misclassification at inference time. W
arXiv:2607.01280v1 Announce Type: new Abstract: Programming-by-example systems infer programs from a small set of input-output examples. Robust PBE work usually models wrong examples as samples from a
arXiv:2607.01530v1 Announce Type: cross Abstract: Understanding user intent is fundamental to delivering relevant search results in e-commerce. However, substantial fraction of real-world queries are
arXiv:2607.01764v1 Announce Type: new Abstract: Repository-level vulnerability reproduction is a demanding software engineering (SE) task: an agent must inspect a codebase, infer the input grammar tha
arXiv:2503.21796v2 Announce Type: replace-cross Abstract: Self-supervised learning has become an increasingly important paradigm in the domain of machine intelligence. Furthermore, evidence for self-s
arXiv:2602.10545v2 Announce Type: replace-cross Abstract: Modern large-scale neural networks are often trained and released in multiple sizes to accommodate diverse inference budgets. To improve effic
arXiv:2607.01444v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models offer inference speedups via selective activation but impose substantial memory requirements because the whole network
arXiv:2607.01602v1 Announce Type: new Abstract: SRAM-based FPGAs provide an attractive platform for energy- and latency-constrained CNN inference at the network edge, yet transient faults can lead to
arXiv:2607.02413v1 Announce Type: cross Abstract: Here we describe the quantum gas analysis and inference (Q-GAIN) Python package, which enables rapid deployment of machine learning (ML) and physics-i
arXiv:2607.01520v1 Announce Type: new Abstract: Transformer inference on long sequences is expensive because softmax attention repeatedly reads from a large KV cache. The prevalent approach to this bo
arXiv:2607.01686v1 Announce Type: new Abstract: Foundation models are routinely released to the public, yet the data recipes used to train them -- such as domain mixture weights that determine how dif
arXiv:2607.00678v1 Announce Type: new Abstract: Mobile manipulation is a key capability for general-purpose robots, yet remains challenging for current embodied learning methods. VLA policies are typi
arXiv:2607.00001v1 Announce Type: new Abstract: Most approaches to AI alignment treat human preferences as fixed targets to be inferred and optimized. This assumption conflicts with extensive empirica
arXiv:2511.05747v3 Announce Type: replace Abstract: Chain-of-Thought (CoT) reasoning enhances the problem-solving ability of large language models (LLMs) but leads to substantial inference overhead, l
arXiv:2607.01127v1 Announce Type: new Abstract: Quantization has become an invaluable tool to reduce memory requirements and inference speed of modern language models, in particular to make them avail
arXiv:2607.00887v1 Announce Type: new Abstract: Low-altitude Unmanned Aerial Vehicles (UAVs) often need to infer channel knowledge across a range of heights from only sparse observations collected at
NVIDIA Confidential Computing addresses data privacy and security concerns for AI workloads by protecting data during inference and engagement with models, offering high-performance protection in loca
arXiv:2607.01067v1 Announce Type: cross Abstract: As an essential modality for dexterous and contact-rich tasks, tactile sensing provides precise force feedback that cannot be reliably inferred from v
Diffusion (Large) Language Models (dLLMs) now match the downstream performance of their autoregressive counterparts on many tasks, while holding the promise of being more efficient during inference. O