本期的 5 篇论文如下:
[00:25] 💡 The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm(LLM 量化的几何学:GPTQ 作为 Babai 最近平面算法)
[00:52] ✨ Deep Researcher with Test-Time Diffusion(基于测试时扩散的深度研究智能体)
[01:40] 🔧 Specification Self-Correction: Mitigating In-Context Reward Hacking Through Test-Time Refinement(规范自校正:通过测试时细化缓解上下文奖励破解)
[02:12] 🚗 PRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Driving(PRIX:从原始像素学习规划实现端到端自动驾驶)
[03:07] 🤖 Chat with AI: The Surprising Turn of Real-time Video Communication from Human to AI(与AI聊天:实时视频通信从人到AI的惊人转变)
【关注我们】
您还可以在以下平台找到我们,获得播客内容以外更多信息
小红书: AI速递
Thông Tin
- Chương trình
- Tần suấtHằng ngày
- Đã xuất bảnlúc 00:00 UTC 29 tháng 7, 2025
- Thời lượng4 phút
- Xếp hạngSạch