Search: “inference”

arXiv:2608.14161v1 Announce Type: new Abstract: LLMs exhibit social biases that can produce inaccurate and discriminatory inferences, posing risks in high-stakes applications. While prior work has mad

arXiv:2608.13774v1 Announce Type: new Abstract: Markov chain Monte Carlo (MCMC) requires only the ability to evaluate the likelihood, making it a common technique for inference in complex models. Howe

arXiv:2608.14191v1 Announce Type: cross Abstract: The key-value (KV) cache stores information from past tokens and is a major memory bottleneck in long-context inference. Existing quantization methods

arXiv:2608.13966v1 Announce Type: cross Abstract: As large language model inference shifts toward lower precision, post-training quantization (PTQ) becomes increasingly brittle, making quantization-aw

arXiv:2608.13929v1 Announce Type: new Abstract: Diffusion models have achieved impressive results in image, video, and streaming generation. However, compared to traditional 3D rendering, they still l

Yutori's browser-use agents run in tight loops: screenshot, action, repeat, dozens of times per task. On Together AI, their Navigator model beats frontier performance at 2x faster inference and 4-5x l

arXiv:2608.12350v1 Announce Type: cross Abstract: The energy demand growth and environmental impacts of artificial intelligence (AI) have generated substantial interest in supplying sufficient low-cos

Qwen3.8-Max is coming to Nebius Token Factory on Day 0. Great to kick things off together with Nebius as our Day 0 launch partner, bringing dedicated inference to more users. Big model, right from the

arXiv:2608.11770v1 Announce Type: new Abstract: Edge-deployed vision systems in target recognition, surveillance, autonomous vehicles, and drone domains require hierarchical inference pipelines where

OpenVINO: Qwen3.5, memory optimization, and test-recurrent-state-rollback (#26952) OpenVINO backend: 1) enable gpt-oss moe on OV bk; 2) enable mxfp4 support OpenVINO backend: disable TOPK_MOE op test

arXiv:2608.12259v1 Announce Type: new Abstract: Financial forecasting models are typically developed in full precision, yet production deployment often requires low-precision inference to reduce memor

Connect your coding agents to AI Gateway with a single command. • Auto-configure 8 popular coding harnesses • 300+ models from 30+ providers, no markup • Open-weight models with ZDR & US inference ▲ ~

arXiv:2608.11354v1 Announce Type: new Abstract: Modern recommender systems treat observed actions as reliable proxies for user preferences, yet interactions often reflect exploration or comparison rat

arXiv:2608.12150v1 Announce Type: new Abstract: Standard evaluation of large language models assumes stable model rankings across inference conditions. We challenge this assumption by varying the toke

arXiv:2608.10690v1 Announce Type: new Abstract: Pretraining corpus composition shapes LLM capabilities, but it often remains hidden even when model weights are released. Prior work has inferred corpus

arXiv:2608.10545v1 Announce Type: cross Abstract: Edge LLMs must preserve inference continuity when a user hands over between edge nodes, requiring key-value (KV) cache transfer to the target node. Ho

arXiv:2608.10628v1 Announce Type: cross Abstract: Long-document understanding often requires reasoning over many visually rich pages, making inference costly and prone to context rot. In this work, we

arXiv:2602.09924v4 Announce Type: replace-cross Abstract: Running LLMs with extended reasoning on every problem is expensive, but determining which inputs actually require additional compute remains c

arXiv:2608.08868v1 Announce Type: new Abstract: Many modern AI systems analyze conversational traces to infer aspects of human interaction and state, implicitly assuming that such information is recov

arXiv:2608.09250v1 Announce Type: new Abstract: Federated learning (FL) must serve devices with varying computational capabilities. A fixed model cannot suit all devices, while training one model per

arXiv:2608.07663v1 Announce Type: cross Abstract: When videos extend from hours to days, directly processing them end-to-end becomes impractical for current Multi-modal Large Language Models (MLLMs).

arXiv:2608.08382v1 Announce Type: new Abstract: As LLM inference shifts to multi-tenant GPU clusters, co-batching improves throughput but obscures per-tenant usage and limits control. Enabling fractio

arXiv:2608.08165v1 Announce Type: new Abstract: Computational models of blood clotting improve understanding of thrombus formation, but their clinical application remains limited because many model in

arXiv:2608.09222v1 Announce Type: new Abstract: Inverse decision modeling infers latent properties of decision processes from observed behavior, but existing formulations rely primarily on action traj

arXiv:2506.07223v2 Announce Type: replace Abstract: Large language models (LLMs) have substantially improved the planning capabilities of embodied agents, enabling their deployment in dynamic and safe

arXiv:2608.09492v1 Announce Type: new Abstract: World Action Models (WAMs) jointly predict future actions and the evolution of the environment. At each inference, a WAM generates a chunk of actions an

arXiv:2608.09351v1 Announce Type: cross Abstract: Test-time scaling improves LLM accuracy but multiplies inference cost, making the accuracy gained per unit of compute the metric that matters in deplo

arXiv:2608.06526v1 Announce Type: new Abstract: Large language models can infer sensitive personal attributes, such as age, location, and occupation, from ordinary text, turning everyday writing into

What’s the best way to recommend products to little-known users? We’ve spent our careers trying to solve this problem for major companies like Spotify and Priceline, and it’s why Sidd founded Malachyt

arXiv:2608.06411v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) achieve strong performance across diverse vision-language tasks, but their efficiency is limited by the cost of

arXiv:2503.03556v3 Announce Type: replace Abstract: Object affordance reasoning, the ability to infer object functionalities based on physical properties, is fundamental for task-oriented planning and

arXiv:2608.05604v1 Announce Type: cross Abstract: Large Language Models (LLMs) increasingly act as agents whose procedural knowledge is stored in reusable skill packages and loaded at inference time.

arXiv:2608.05833v1 Announce Type: new Abstract: Knowledge graph completion (KGC) aims to infer missing entities or relations from incomplete graph structures, and has evolved into multimodal knowledge

A regulated customer needed all Claude Code inference processed in a single AWS Region (London), not just in-geography. This post shows two ways to pin Claude Code on Amazon Bedrock to one Region: an

arXiv:2602.19161v2 Announce Type: replace Abstract: Latent diffusion models have enabled high-quality video synthesis, yet their inference remains costly and time-consuming. As diffusion transformers

Gary Marcus won! @GaryMarcus I would have assumed it was fairly obvious, but in case it's not: a million-line codebase (also known as a 'harness'), running at inference time, orchestrating thousands o

arXiv:2608.04624v1 Announce Type: cross Abstract: Current neural networks for beat tracking generate invalid outputs, such as consecutive downbeats and erratic tempo changes, even when these are not p

arXiv:2608.04569v1 Announce Type: new Abstract: Hard prompt compression reduces long-context inference cost by independently scoring tokens, sentences, or chunks and retaining the highest-scoring unit

arXiv:2608.03015v1 Announce Type: cross Abstract: Pretrained large language models (LLMs) have demonstrated in-context learning (ICL) capabilities for numerical inference over sequences serialized as

arXiv:2608.03204v1 Announce Type: cross Abstract: Post-training reinforcement learning (RL) algorithms are commonly used to align large vision-language models (LVLMs) with human intent and the require

arXiv:2403.16178v2 Announce Type: replace-cross Abstract: For effective human-agent teaming, robots and other artificial intelligence (AI) agents must infer their human partner's abilities and behavio

arXiv:2608.02691v1 Announce Type: cross Abstract: The key-value (KV) cache has become a major memory and bandwidth bottleneck in long-context large language model inference, making ultra-low-bit quant

arXiv:2512.01370v2 Announce Type: replace-cross Abstract: Diffusion-based solvers for partial differential equations (PDEs) are often bottle-necked by slow gradient-based test-time optimization routin

arXiv:2608.03921v1 Announce Type: new Abstract: This paper offers a new interpretation of the Transformer during inference. Against the 'stochastic parrot' view that large language models merely repro

arXiv:2608.01885v1 Announce Type: new Abstract: While deep learning models have achieved state-of-the-art performance in time series anomaly detection, their complex architectures incur substantial in

arXiv:2608.00902v1 Announce Type: new Abstract: LLM agents accumulate long trajectories of reasoning steps, tool calls, and environment feedback, making the KV cache a major inference bottleneck. KV c