言栖资讯收录 139918 篇 AI、开发与建站文章（English），按发布时间排序，支持搜索与按语言筛选。
arXiv:2608.01651v2 Announce Type: replace Abstract: Emerging LLMs increasingly interleave full attention with recurrent linear attention to reduce long-context …
arXiv:2604.15279v2 Announce Type: replace Abstract: Hybrid High-performance Computing (HPC)-quantum workloads based on circuit cutting decompose large quantum c…
arXiv:2603.10342v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as AI agents that operate in short reasoning-action l…
arXiv:2509.26092v3 Announce Type: replace Abstract: Distributed deep learning is critical for training convolutional neural network (CNN) models on large-scale …
arXiv:2502.21012v3 Announce Type: replace Abstract: Unsupervised image anomaly detection (UAD) has become a critical process in industrial and medical applicati…
arXiv:2611.08363v1 Announce Type: cross Abstract: Quantization reduces the memory and bandwidth demands of large language model (LLM) inference but can degrade …
arXiv:2611.08307v1 Announce Type: cross Abstract: Diffusion language models can write many tokens per step, but must choose which tokens are safe to commit toge…
arXiv:2611.08306v1 Announce Type: cross Abstract: We present \textsc{Ginger}, a state-of-the-art open-source C++ library for graph-based approximate nearest nei…
arXiv:2611.08083v1 Announce Type: cross Abstract: Replicated data types providing strong eventual consistency offer a principled foundation for developing decen…
arXiv:2611.07164v1 Announce Type: cross Abstract: Provenance Identity Continuity (PIC) represents an authority-use event as an operation/resource behavior situa…
arXiv:2611.07159v1 Announce Type: cross Abstract: Proof-of-Possession (PoP) establishes that an executor controls an artifact (key, token, credential, or capabi…
arXiv:2611.06989v1 Announce Type: cross Abstract: Enterprises run business transactions through multi-agent AI systems spanning clouds, large language models (L…
arXiv:2611.06984v1 Announce Type: cross Abstract: Reinforcement learning post-training improves the capabilities of large language models, but generating traini…
arXiv:2611.08108v1 Announce Type: new Abstract: Field devices deployed today will still be producing records when quantum computers may break their signatures, …
arXiv:2611.08076v1 Announce Type: new Abstract: Local certification allows network vertices to verify global properties using certificates from an untrusted pro…
arXiv:2611.08060v1 Announce Type: new Abstract: The Common Community Physics Package (CCPP) is a framework designed to simplify the exchange of physics packages…
arXiv:2611.08023v1 Announce Type: new Abstract: Complete-block offloading reduces model residency but requires each transferred block to fit the GPU budget. We …
arXiv:2611.07996v1 Announce Type: new Abstract: Multi-agent reinforcement learning (MARL) is increasingly used in systems where many entities interact in a shar…
arXiv:2611.07928v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) is a standard approach to enhance the reliability of large language model (…
arXiv:2611.07919v1 Announce Type: new Abstract: We present a novel approach for model checking fault-tolerant distributed algorithms: instead of building large,…