一篇系统梳理LLM后训练中强化学习的综述，涵盖RLHF、DPO、RLVR等前沿方法
arXiv:2407.16216v4 Announce Type: replace Abstract: Large language models (LLMs) trained via pretraining and supervised fine-tuning (SFT) can still pr…
脉冲神经网络的局部学习规则综述与基准测试框架，助你快速理解不同训练算法的差异与适配场景
arXiv:2605.15058v1 Announce Type: cross Abstract: The rapid expansion of spiking neural networks (SNNs) has led to a proliferation of training algorit…
综述RAG系统可信度挑战，涵盖事实性、鲁棒性与公平性等关键维度。
arXiv:2409.10102v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has quickly grown into a pivotal paradigm in the develo…
全面梳理RAG在NLP领域的研究进展，涵盖方法、应用与未来方向，适合研究人员和从业者快速了解前沿。
arXiv:2407.13193v4 Announce Type: replace Abstract: Large language models (LLMs) have achieved strong empirical performance in various fields, benefit…
综述探讨基础模型在个性化联邦智能中的应用，汇总当前方法、挑战与未来方向。
arXiv:2505.06907v2 Announce Type: replace-cross Abstract: The rise of large language models (LLMs), such as ChatGPT, Gemini, and Grok, has reshaped th…
大模型驱动的生成式AI正颠覆传统文献综述流程，摘要、问答、数据提取等能力让科研效率起飞。
arXiv:2605.16475v1 Announce Type: cross Abstract: Generative artificial intelligence (GenAI), based on large-language models (LLMs), such as ChatGPT, …
梳理视觉-语言模型持续学习最新综述，超越遗忘视角解读多模态大模型演进挑战
arXiv:2508.04227v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) and the recent surge of Multimodal Large Language Models (MLLM…
首份大模型在线策略蒸馏综述，系统梳理方法、挑战与未来方向，适合研究者深挖。
arXiv:2604.00626v3 Announce Type: replace Abstract: As Large Language Models (LLMs) continue to grow in both capability and cost, transferring frontie…
系统性综述揭示合成表格健康数据评估的关键挑战与指南，为数据质量评估提供严谨框架
arXiv:2504.18544v3 Announce Type: replace-cross Abstract: Generating synthetic tabular health data is challenging, and evaluating their quality is equ…
一份系统梳理图到视频扩散模型发展的综述，从理论基础到前沿开放问题，助研究者快速把握领域脉络。
arXiv:2605.17248v1 Announce Type: new Abstract: Diffusion-based \textit{image-to-video} (I2V) generation has become a central direction in generative …
AWS 2026新动态、Amazon Quick与OpenAI合作，云服务最新周报速览。
Last week, I took some time off in York, England, often described as the most haunted city in the country. I wandered through the ruins of abbeys that…
系统梳理38篇同行研究，揭示LLM在网页无障碍中的真实图景：多数聚焦文本任务，依赖通用模型与提示工程，却鲜有人真正让残障用户参与评测。这份综述是研究者和实践者绕不开的现状地图。
arXiv:2605.13873v1 Announce Type: cross Abstract: Web accessibility aims to ensure that web content and services are usable by people with diverse abi…