2026-11-18 AI 日报
统计日时区:America/Los_Angeles · 尚未结算
morluto/rea · deepseek-ai/deepseek-harness · paperclipai/paperclip
开源项目
- morluto/rea
Reverse engineer anything with agents, from app behavior down to native binaries.
- deepseek-ai/deepseek-harness
DeepSeek Harness: Everything is a Plugin.
- paperclipai/paperclip
The open-source app everyone uses to manage agents at work
- dograh-hq/dograh
Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow…
- basketikun/chatgpt2api
ChatGPT 官网接口纯协议逆向实现,Go 语言编写,高并发、低内存、高性能。指纹级请求还原,支持 GPT-Image-2.6 生图/改图、GIF 动图、文本模型与语音合成/转写,兼容 OpenAI 接口协议,在线批量生图,号池管理,支持导入 CPA、sub2api 号池,可接入 Cherry…
- HKUDS/RAG-Anything
"RAG-Anything: All-in-One RAG Framework"
- datawhalechina/llm-algo-leetcode
Hands-on LLM algorithms and systems with PyTorch, Triton & CUDA.《大模型算法与系统教程》:模型架构与训练、后训练、推理加速、性能与算子优化,配套 Notebook 练习、答案解析、测试与实验。
- ed-donner/agents
Repo for the Complete Agentic AI Engineering Course
- ed-donner/llm_engineering
Repo to accompany my mastering LLM engineering course
- GoogleCloudPlatform/generative-ai
Sample code and notebooks for Generative AI on Google Cloud, with Gemini platform
论文
- AscendGYM: A Cost-Aware Kernel Optimization Benchmark for Real-World Workloads on Ascend NPUs
Kernel optimization is essential for efficient large language model (LLM) training and inference on Ascend NPUs. Existing Ascend kernel benchmarks primarily…
- TeleChat to Xing4: Advancing Frontier Agentic Models on Domestic Chips and Frameworks
We present Xing 4, a series of large language models that extends the TeleChat lineage through coordinated advances in model architecture and training…
- Weight-Space Programming Doesn't Need Transformers
Standard neural architectures such as the Transformer were chosen because they train well with gradient descent and run fast on GPUs. In weight-space…
- ForceHarness: Turning Force into Action and Physics for Frozen Frontier Models
Frontier multimodal models can now control robots zero-shot from images, yet many manipulation tasks depend on contact forces that images cannot show.…
- Multi-Branch Transformer
Transformer language models are commonly scaled by making their blocks wider or stacking them deeper. In this work, we explore a complementary path:…
- TCP4D: A Unified Tool-Center-Point Tracking and Generation Model for Robot Manipulation
Robot manipulation videos provide a rich visual experience, yet recovering robot action and gripper-state annotations from RGB observations still remains…
- FastFrames: Video Generation at Interactive Latency
Autoregressive video diffusion models generate frames based on new observations and inputs, making them a promising medium for interactive visual experiences.…
- Breath-Dx: A Time Series Classification Benchmark for Disease Screening with eNose
Electronic nose (eNose) technology offers a portable, non-invasive route for disease screening via exhaled breath analysis. However, progress in the field is…
- Self-Improvement Memory Enables Continual Recursive Self-Improvement
Harness optimization is often studied with a fixed policy model and benchmark. When either changes, the optimizer must decide which parts of an evolved…
- Heave-Ho: Decentralized Long-Horizon Multi-Humanoid Collaboration
Collaboration promises to extend humanoid capabilities beyond what individual robots can achieve. However, realizing this potential requires coordinated…
行业新闻
本统计日暂无条目。
社区动态
本统计日暂无条目。
官方发布
- Introducing GPT-6.2 Astra and Sol
Introducing GPT‑6.2 Astra and Sol, with better professional outputs, coding, computer use, and efficiency at lower cost across ChatGPT Work, Codex, and the API.
- Gemini 4 Hydrogen: a faster model for general purpose robotics
Google's Gemini 4 Hydrogen brings strong spatial and embodied reasoning capabilities to a fast, efficient model built specifically for robotics. To help…
- Multimodal file processing and slicing
You can now pass Microsoft Office and OpenDocument files (Word, PowerPoint, and Excel) directly to the Gemini API, and slice documents, spreadsheets, videos,…
- Le Groupe Figaro and OpenAI partner to bring Le Figaro journalism to ChatGPT
Le Groupe Figaro and OpenAI partner to bring Le Figaro’s journalism to ChatGPT through summaries and excerpts, with links to original stories.
- codex 0.170.0
New Features Added WebRTC negotiation for realtime voice calls in the TUI. (#61172) Added automatically refreshed authentication headers for OpenTelemetry…
- Voice editing in Gemini 3.5 Transcribe
gemini-3.5-transcribe and gemini-3.5-transcribe-live now support voice-driven editing, rewriting, and formatting of dictated speech or pre-existing text…
- We’ve launched Linked billing in beta with the user-profiles-billing-2026-10-01 beta header.
We’ve launched Linked billing in beta with the user-profiles-billing-2026-10-01 beta header. Your customers can now pay for the Claude usage in your app…
- Choose a release channel in Claude Desktop
You can now use a release channel to set which version of Claude Desktop you get when the app updates. Stable stays the default and gets new versions less…
- Muse Is Now Available in Australia: The World’s First Personal AI Agent Built for Everyone
Muse is available in Australia from today, with local connector experiences across creativity, shopping, property, fitness and entertainment rolling out…
- Text generated by Claude Opus 4.6, Claude Opus 4.5, Claude Sonnet 4.5, and Claude Haiku 4.5 carries Anthropic’s text…
Text generated by Claude Opus 4.6, Claude Opus 4.5, Claude Sonnet 4.5, and Claude Haiku 4.5 carries Anthropic’s text watermark on supported platforms. How…