Search: “inference”

arXiv:2607.22688v1 Announce Type: new Abstract: Post-training agents for automated AI research requires optimizing not only model parameters, but also the runtime harness that shapes how research traj

arXiv:2602.06127v2 Announce Type: replace Abstract: The high computational demands of Large Language Models (LLMs) motivate methods that reduce parameter count and accelerate inference. In response, m

arXiv:2607.24312v1 Announce Type: new Abstract: Document-level relation extraction (DocRE) aims to extract relations among multiple entities across extended contexts while maintaining consistency acro

arXiv:2607.22602v1 Announce Type: new Abstract: Inference-time scaling has emerged as a powerful paradigm for improving large language model reasoning, often delivering larger gains on difficult reaso

arXiv:2607.22679v1 Announce Type: new Abstract: In visually-rich documents, information is encoded not only in individual page objects such as tables, headers, and text blocks, but also in the structu

arXiv:2607.22565v1 Announce Type: new Abstract: With the widespread deployment of edge-side AI inference, edge platforms are increasingly required to support latency-sensitive, highly concurrent, and

arXiv:2607.24331v1 Announce Type: new Abstract: As the inference phase of Large Language Models (LLMs) requires handling long context windows, the Key-Value (KV) cache initially appears to address thi

arXiv:2607.22785v1 Announce Type: cross Abstract: Apple-Silicon SoCs share CPU, GPU, and Neural Engine over one unified memory system, raising the question of whether transformer inference can be acce

I've been digging into Krea2 to see if there's any way to condition inference in specific regions of pixel -> latent space to implement bbox type prompting in order to apply multiple simultaneous char

arXiv:2607.24555v1 Announce Type: cross Abstract: Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read in full at every decode step. Attention keys

arXiv:2607.22564v1 Announce Type: new Abstract: Convolutional neural networks often contain redundant feature maps that increase storage and inference cost. This paper presents a loss-aware feature-ma

arXiv:2607.22629v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) produce long, explicit chains of intermediate steps before generating a final answer at inference time. These intermediate

arXiv:2607.23607v1 Announce Type: cross Abstract: Molecular structure elucidation from tandem mass spectra (MS/MS) is a central inverse problem in analytical chemistry. Most existing approaches to MS/

arXiv:2502.04678v2 Announce Type: replace Abstract: Repeated first-price auctions are contextual decision problems with censored but reusable feedback: after submitting a bid, a learner can infer the

arXiv:2607.23445v1 Announce Type: cross Abstract: Omnimodal large language models (OmniLLMs) are rapidly extending multimodal reasoning to cover synchronized audio and video. However, the resulting au

arXiv:2607.22786v1 Announce Type: cross Abstract: In this work, we explore how the inference time of a Transformer Neural Network can be efficiently optimized with applications to real-time anomaly de

arXiv:2601.16249v3 Announce Type: replace-cross Abstract: Learning DAG structures from purely observational data remains a long-standing challenge across scientific domains. An emerging line of resear

arXiv:2607.24583v1 Announce Type: new Abstract: Large scale Bayesian nonparametrics (BNP) learner such as Stochastic Variational Inference (SVI) can handle datasets with large class number and large t

arXiv:2607.23517v1 Announce Type: new Abstract: We present a real-time human-centric world model for upper-body interactive generation, aiming to synthesize coherent local world dynamics centered on a

arXiv:2511.12940v2 Announce Type: replace Abstract: Recent advancements in video generation has shifted from bidirectional models for short videos to autoregressive ones for ultra long video generatio

arXiv:2607.22913v1 Announce Type: new Abstract: Detecting pollinators in field video is challenging: targets are small, visually similar, and observed against cluttered vegetation under blur and occlu

arXiv:2607.23735v1 Announce Type: cross Abstract: In many real-world scenarios, encountering continual shifts in domain during inference is very common. Consequently, continual test-time adaptation (C

arXiv:2607.23991v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly controlled through system prompts that specify roles, styles, formats, and safety requirements. However,

arXiv:2607.22762v1 Announce Type: cross Abstract: Causal inference has become a central issue across various fields, including computer science, statistics, economics, education, healthcare, and medic

arXiv:2607.23581v1 Announce Type: new Abstract: Multimodal misinformation verification is challenging because misleading signals may come from different parts of a post and require different forms of

arXiv:2607.21804v1 Announce Type: cross Abstract: Lossless acceleration schemes, such as speculative decoding, promise significant inference speedups by relying on dynamic token-level alignment betwee

arXiv:2607.21623v1 Announce Type: new Abstract: We present EaaS, a cloud-native reference architecture that operationalizes AI evaluation methods as six stateless Kubernetes microservices: conformal p

Kimi K3 is now available directly from its Hugging Face model page through Together AI, give it a try! Kimi K3 in @huggingface Inference Providers is live via @togethercompute 3/M input tokens, 15/M o

Kimi K3 is now live on @togethercompute! Happy to have Together AI as our day0 launch partner, giving developers immediate access to K3 through high-throughput inference optimized for coding agents an

arXiv:2607.22430v1 Announce Type: new Abstract: Learning world models that infer environment dynamics from high-dimensional observations and predict outcomes under candidate actions is central to plan

arXiv:2607.14193v2 Announce Type: replace-cross Abstract: The Helmholtz equation governs time-harmonic wave propagation, and in dissipative media a complex modulus renders its squared wavenumber kappa

arXiv:2607.22535v1 Announce Type: cross Abstract: Action-conditioned video world models predict future observations from an initial observation and an action signal. In robotics, actions influence fut

arXiv:2607.22355v1 Announce Type: new Abstract: Inferring physical properties such as mass, stiffness, and elasticity from a single image is essential for simulation and embodied AI, yet most existing

What quantization or storage size tiers should we expect further down the line? This site suggests q4 and q8 are coming. But I don't know how to translate that to storage size for local inference. htt

The market for data center GPUs is evolving beyond individual chip specifications into a contest over fully integrated rack-scale systems. As AI workloads scale into the gigawatt range, buyers increas

arXiv:2512.12086v2 Announce Type: replace Abstract: Data obfuscation is a promising technique for mitigating attribute inference attacks by semi-trusted parties with access to time-series data emitted

arXiv:2607.20538v1 Announce Type: cross Abstract: Long-context Transformer inference increasingly relies on KV-cache compression or quantization. Prior rotation and transform-coding results suggest th

arXiv:2607.20469v1 Announce Type: new Abstract: Large language models (LLMs) handle many tasks with one set of parameters, but under KV-cached inference it is unclear what task-general structure, if a

arXiv:2607.20457v1 Announce Type: cross Abstract: Inference with large language models (LLMs) on long sequences is computationally expensive due to the quadratic complexity of self-attention. Distribu

arXiv:2605.11936v2 Announce Type: replace Abstract: Recent soft prompt research has tried to improve reasoning by inserting trained vectors into LLM inputs, yet whether the gain comes from the learned

OpenAI GPT-5.6 Sol, Terra, and Luna are now generally available on Amazon Bedrock. Learn how to select a model, run inference through the Responses API on the bedrock-mantle endpoint, reduce cost with

This post covers Opus 5’s improvements and practical guidance for AI engineers integrating the model into agentic systems and production inference workloads on Amazon Bedrock. See the documentation fo

arXiv:2607.21179v1 Announce Type: new Abstract: The goal of this paper is to reduce the input token cost of Omni-modal large language models (Omni-LLMs) at inference time. Omni-LLMs reason jointly ove

arXiv:2607.20482v1 Announce Type: new Abstract: Recent advances in large language models have enabled web agents to autonomously execute complex tasks. In practice, users frequently provide underspeci

arXiv:2607.20475v1 Announce Type: new Abstract: Sampling in LLM inference comprises a combinatorial set of logit processing, token selection, and verification operations for speculative decoding. Howe

arXiv:2603.06642v2 Announce Type: replace-cross Abstract: Test-Time Training (TTT) language models replace the KV-cache with fast weights updated during inference, achieving O(1) memory but suffering