SlimPer: Make Personalization Model Slim and Smart
SlimPer提出让个性化模型精简且智能的新方法,兼顾性能与效率,值得关注。
arXiv:2607.12281v1 Announce Type: cross Abstract: Transformer-style architectures are increasingly adopted for industrial recommendation systems, yet …
SlimPer提出让个性化模型精简且智能的新方法,兼顾性能与效率,值得关注。
arXiv:2607.12281v1 Announce Type: cross Abstract: Transformer-style architectures are increasingly adopted for industrial recommendation systems, yet …
智能体不再依赖自然语言,直接在潜在空间高效沟通,突破传统交互瓶颈。
arXiv:2511.09149v5 Announce Type: replace-cross Abstract: While natural language is the de facto communication medium for LLM-based agents, it present…
无需隐变量,三值量化LLM训练新方法,开源项目BitBop让你以极低成本体验高效训练。
Article URL: https://github.com/ValerioDolci/bitbop Comments URL: https://news.ycombinator.com/item?id=48892013 Points: 1 # Comments: 1
IT之家 7 月 12 日消息,特斯拉日前发布了 《2025 年影响力报告(Impact Report)》,其中披露了大量有关即将推出的 Cybercab 自动驾驶出租车的新细节。 这款专为 Robotaxi 打造的车型将重新定义共享出行,此次报告首次较为完整地介绍了 Cybercab 所采用的硬件…
突破LLM持续微调遗忘瓶颈,ReCoLoRA以频谱感知递归合并实现任务序列高效学习。
arXiv:2607.07719v1 Announce Type: new Abstract: Parameter-efficient fine-tuning adapts a large language model to one task cheaply, but across a task s…
IT之家 7 月 8 日消息,据科技日报,历经十余年持续攻关,我国在农林生物质资源化利用领域取得重要突破,实现了生物炭的大规模高效制备。 7 月 5 日,由合肥综合性国家科学中心环境研究院牵头完成的“面向高值功能碳基材料创制的农林生物质高效转化关键技术与装备”科技成果评价会在安徽合肥举行。由两院院士…
面向低资源语言罗马尼亚语的多模态指令微调,用参数高效方法实现视觉语言模型适配,填补非英语VLM研究空白。
arXiv:2512.14926v2 Announce Type: replace-cross Abstract: Focusing on low-resource languages is an essential step toward democratizing generative AI. …
LLM领域新突破:神经元感知主动少样本学习,精准挑选标注样本,大幅节省人力成本。
arXiv:2607.02423v1 Announce Type: cross Abstract: Active Few-Shot Learning (AFSL) adapts LLMs to specialized domains by identifying the most valuable …
探索参数高效LLM架构新突破,为边缘部署提供解决方案。
arXiv:2604.21254v3 Announce Type: replace Abstract: LLM architecture research generally aims to maximize model quality subject to fixed compute/latenc…
多模态大模型新方法,实现视觉token高效嵌入,已被ECCV 2026录用。
arXiv:2602.05275v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have shown immense promise in universal multimodal retrie…
消息传递方法实现高效推理,揭秘AI全新思维范式
arXiv:2607.01077v1 Announce Type: cross Abstract: While inference-time scaling has improved the reasoning abilities of large language models (LLMs), t…
基于几何原理的随机优化方法,为大规模语言模型训练效率提供新思路
arXiv:2510.01878v2 Announce Type: replace Abstract: Low-rank gradient optimization for large language models is currently divided into two categories:…
探讨LLM在高效学习中的可信度矛盾,引发现实思考。
Reading some threads here on HN recently, people suggest LLMs give out untrustworthy data. That makes me think they are not a good source to understan…
在RTX 5070上微调4B参数模型,实现高效轻量推理,消费级硬件也能玩大模型。
The goal was to create a highly efficient, small-scale model that can perform reasoning tasks while remaining lightweight enough to run easily on cons…
阿里千问语音输入法macOS版,语音秒变工整文字,AI自动润色,最快300字/分,说完即成稿。
IT之家 6 月 27 日消息,阿里旗下千问输入法 macOS 版今日已上线官网,官方预告 iOS 版、 Android 版、Windows 版将于近日发布。 官网显示,该产品号称“说完即成稿”, 支持 最快 300 字 / 分 ,AI 自动润色,说话秒变工整文字。支持 9 种方言,纯净无广告。 此…
掌握提示工程,让AI输出更精准高效,提升人机协作效果。
Artificial Intelligence tools like ChatGPT, Gemini, Claude, Cursor, and Copilot have changed the way we work. However, many people are not getting the…
百度开源端到端OCR模型,总参30亿仅激活5亿,有效解决文档解析越生成越慢问题
IT之家 6 月 25 日消息,百度于 6 月 22 日开源推出 Unlimited OCR 模型,总参数量 30 亿,推理时仅激活 5 亿参数 ,目标解决在解析长文档时,端到端 OCR 模型越生成越慢的问题。 IT之家注:端到端 OCR 模型是统一神经网络架构系统,融合检测图像中的文本和字符识别,…
BitNet二值化网络实现高效文本嵌入,为资源受限场景提供轻量级NLP新方案。
arXiv:2606.25674v1 Announce Type: new Abstract: LLM-based text embedders have substantially improved retrieval and semantic representation quality, bu…
通过偏好对进行推理时对齐,提出高效方案避免昂贵微调
arXiv:2606.24004v1 Announce Type: cross Abstract: Steering a large language model (LLM) toward a desired behavior typically relies on an iterative pro…