AI 前沿

聚合全球 AI 前沿资讯与洞察,覆盖大模型、机器学习、自然语言处理等最新动态。
今日 24 小时时间轴 →
排序
标签
大模型1,935机器学习980人工智能817强化学习613AI467AI安全435语言模型413大语言模型403自然语言处理386OpenAI370
15M web servers on one VM – smoltcp, DPDK, AF_XDP

15M web servers on one VM – smoltcp, DPDK, AF_XDP

Hacker News 2026-11-19 13:56 原文 1 阅读 热度 20
网络技术虚拟化性能优化
Neural Network-Based Modeling of Hysteretic Systems: From Prandtl and Preisach Neural Networks to Neuro-Madelung and Neuroplastic Continuous Models

Neural Network-Based Modeling of Hysteretic Systems: From Prandtl and Preisach Neural Networks to Neuro-Madelung and Neuroplastic Continuous Models

arXiv机器学习 2026-11-19 13:00 原文 1 阅读 热度 20
Hysteresis is a complex nonlinear phenomenon characterized by memory dependence, path dependence, and, in many physical systems, degradation, non-congruency, asymmetry, and rate dependence. This revie...
神经网络迟滞系统建模
CounselTraj: Synthesizing Process-Aware Psychological Counseling Dialogues via Dialogue-Act Trajectory Planning

CounselTraj: Synthesizing Process-Aware Psychological Counseling Dialogues via Dialogue-Act Trajectory Planning

arXiv自然语言 2026-11-19 13:00 原文 12 阅读 热度 60
The growing demand for psychological counseling has motivated the development of LLM-based systems that support human counselors, but training such systems requires large-scale, high-quality dialogue ...
心理咨询大模型对话生成
Once Upon a Bias: Gender Stereotyping in LLM-Generated Children's Stories

Once Upon a Bias: Gender Stereotyping in LLM-Generated Children's Stories

arXiv自然语言 2026-11-19 13:00 原文 11 阅读 热度 70
Large language models are increasingly used to create stories for children. Since bedtime stories can shape children's perceptions of social roles, this raises concerns about whether LLMs adapt narrat...
大模型AI伦理性别偏见
MIRAGE: A Framework for Multi-hop Reasoning under Dynamic Knowledge Injection

MIRAGE: A Framework for Multi-hop Reasoning under Dynamic Knowledge Injection

arXiv自然语言 2026-11-19 13:00 原文 11 阅读 热度 55
Multi-hop Question Answering (MQA) requires large language models (LLMs) to retrieve and synthesize multiple pieces of evidence into a coherent reasoning path, which is essential for complex tasks. Ho...
多跳推理大语言模型知识注入
Grading Executable Legal Rules Against Independent Records: Transitional Provisions and Korean SME Status

Grading Executable Legal Rules Against Independent Records: Transitional Provisions and Korean SME Status

arXiv自然语言 2026-11-19 13:00 原文 10 阅读 热度 68
Laws are increasingly turned into programs that decide cases, such as whether a firm was a small or medium enterprise (SME) on a given date, and large language models (LLMs) now write them. The progra...
大模型AI法律法律科技
A Hybrid RAG Framework for Deceptive Review Detection: Integrating RoBERTa-LoRA, FAISS-Based Retrieval, and LLM Reasoning

A Hybrid RAG Framework for Deceptive Review Detection: Integrating RoBERTa-LoRA, FAISS-Based Retrieval, and LLM Reasoning

arXiv自然语言 2026-11-19 13:00 原文 12 阅读 热度 65
The growth of deceptive online opinions poses a critical risk of misinformation and fraud. This paper proposes a Retrieval-Augmented Generation (RAG) system to automatically distinguish spam reviews. ...
检索增强生成虚假评论检测大模型
Compression Effects on Low-Resource Multilingual Translation

Compression Effects on Low-Resource Multilingual Translation

arXiv自然语言 2026-11-19 13:00 原文 11 阅读 热度 45
We present a pilot study characterising the effect of post-training quantisation on multilingual machine translation quality and inference cost for three African languages - Hausa, Swahili, and Yoruba...
量化技术多语言翻译低资源语言
A Mechanistic Analysis of In-Context Learning and Out-of-Context Hallucination

A Mechanistic Analysis of In-Context Learning and Out-of-Context Hallucination

arXiv自然语言 2026-11-19 13:00 原文 11 阅读 热度 62
Large language models can infer and follow specific rules through in-context learning (ICL), yet may fail to remain faithful to provided evidence, giving rise to out-of-context (OOC) hallucination. Ex...
大语言模型上下文学习幻觉分析
ReflectRec: Cycle-Consistency Preference Verification for LLM-based Recommendation

ReflectRec: Cycle-Consistency Preference Verification for LLM-based Recommendation

arXiv自然语言 2026-11-19 13:00 原文 11 阅读 热度 60
CoT-style LLM recommenders generate a natural-language preference note as a chain-of-thought prefix to ranking, but the note is trusted without verification, and the ranker never consults behaviorally...
大模型推荐系统思维链
Coverage Governs Accuracy: When to Expand the Lexicon and When to Fall Back in Low-Resource Manchu OCR

Coverage Governs Accuracy: When to Expand the Lexicon and When to Fall Back in Low-Resource Manchu OCR

arXiv自然语言 2026-11-19 13:00 原文 11 阅读 热度 35
Character-level OCR for low-resource Manchu often produces near-miss spelling errors. Lexicon-constrained decoding can correct such errors with lexical knowledge, but a fixed dictionary cannot cover t...
文字识别满语低资源
NarrowSpec: Draft Hidden Width Need Not Match the Target in Speculative Decoding

NarrowSpec: Draft Hidden Width Need Not Match the Target in Speculative Decoding

arXiv自然语言 2026-11-19 13:00 原文 11 阅读 热度 55
Speculative decoding is widely used to speed up generation in large language models (LLMs), with a small draft model proposing tokens that one forward pass of the target model verifies. Draft models t...
推测解码大语言模型推理加速
加载中...
已经到底啦