一篇读懂训练稳定性：Loss Spike、梯度爆炸与数值问题的诊断与修复
从 PaLM 与 OPT 的真实病历出发，拆解 loss spike 的五类根因、回滚跳批的标准操作与 z-loss、软截断等预防手段。
阅读全文 →
全部文章
ARCHIVE 共 465 条Google’s $899 Googlebook is a bet that you’ll buy a new laptop for Gemini
Google’s AI-native Googlebook ties Gemini to the cursor, dictation, widgets, and other parts of the desktop experience.]
You too Google! Google Confirms Gemini Breached 3 Companies in AI Security Tests
Google says Gemini accessed 3 real companies in May by guessing a password and reusing credentials from a public reposit…
Alibaba's open-weight Qwen-Image-2.1 claims to beat closed models in image generation with just 7 billion parameters
Alibaba's Qwen team has released Qwen-Image-2.1, an open-weight model that generates and edits images on powerful consum…
Complex KDA: Understanding and Enhancing the Expressivity of Kimi Delta Attention
Linear RNNs based on the delta-rule enable efficient sequence modeling, but their linear updates with a low-rank correct…
Googlebooks 于 10 月 4 日上市，最低 899 美元]
深度集成 Gemini、运行 Android 的笔记本电脑 Googlebooks 将于 10 月 4 日上市。Google 硬件合作伙伴中除了宏碁推出一款起售价 899 美元的型号外，其余厂商的产品都超过 1000 美元。Googlebo…
早报｜特努斯：iPhone Duo是乔布斯理念体现/小米18 Pro确认涨价/西贝否认倒闭传闻
· Google Gemini 安全测试越界，误攻 3 家真实企业 · 长鑫存储 G5 DRAM 平台量产，单片晶圆裸片数提升至少 50% · 智谱 MaaS 平台将上线数据内容不留存机制 #欢迎关注爱范儿官方微信公众号：爱范儿（微信号：i…
GPT-6 伤人实测曝光：刺向「婴儿」、制造毒气，97% 情况选择照做
当大模型开始拥有一双真实的手 #欢迎关注爱范儿官方微信公众号：爱范儿（微信号：ifanr），更多精彩内容第一时间为您奉上。 ]
Vals AI 使用《我的世界》评测 Open GPT‑6 Astra 模型：显示 AI 遇重大变故可能陷入行为僵局
IT之家 9 月 21 日消息，AI 评测机构 Vals AI 利用游戏《我的世界（Minecraft）》对 OpenAI 最新大模型 GPT‑6 Astra 开展长时自主游戏测试，全程在 Twitch 直播，总测试时长达到 141 小时。…
我国首款藏语多语言全模态 AI 输入法发布，覆盖手机、电脑等全终端
IT之家 9 月 21 日消息，据科技日报昨晚报道，9 月 20 日，在青海师范大学教师教育高质量发展暨建校 70 周年大会科研成果展示环节， 我国首款藏语多语言全模态 AI 输入法 —— 智达 AI 输入法及配套藏文字体集正式发布 。 据…
Alibaba Qwen Team Releases Qwen3.8-LiveTranslate: A Real-Time Interpretation Model That Cuts Average Lag to 2.3 Seconds Across 60 Languages
Qwen has released Qwen3.8-LiveTranslate, a real-time simultaneous interpretation model built on a new Interleave archite…
Google’s Gemini is the latest AI model to hack other companies
Google said Gemini had "acted appropriately" by ending each hack immediately.]
Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs
Personalized large language models are often expected to follow explicit style instructions, yet we find that such instr…