🎮 强化学习 - doxnotejun · Scour

The Exploit Always Wins 🧠思维模式 Blog

abhishek-shankar.com·1d

Good LLM development and usage patterns 💬NLP Blog

blog.bluebyday.com·6d·Hacker News

How to Stop Shipping Low-Quality RL Environments (with Examples) 👁️计算机视觉 News

latent.space·1d·Hacker News

Bridging Multi-Vector and Learned-Sparse Retrieval, A Diagnostic Framework for Robust Semantic IDs, and More! 👁️计算机视觉 News Blog

recsys.substack.com

Lodge School teams advance to volleyball quarter-finals 🧠认知科学

NVIDIA goes open source with a big batch of physical AI agent tools 👁️计算机视觉

helpnetsecurity.com·5d

I got so mad at poke(rogue)like that I trained a RL agent to beat it for me 🤖机器学习 Blog

blog.thiagolira.com.br·2d·Hacker News

NVIDIA Unveils Vera, the CPU for Agents 🗂️知识管理

nvidianews.nvidia.com·6d

ACM CAIS: Conference on AI and Agentic Systems 🧠认知科学 Blog

muratbuffalo.blogspot.com·4d·Blogger

Merging model-based control with multi-agent reinforcement learning for multi-agent cooperative teaming strategies 👁️计算机视觉 Academic

NVIDIA Enables the Next Era Of Physical AI Research With Agent Skills For Autonomous Vehicles, Robotics And Vision AI 🕸️神经网络 Blog

blogs.nvidia.com·3d

Training Deliberative Monitors for Black-Box Scheming Detection 💬NLP

lesswrong.com·2d

Good teachers don’t cheat 🧠认知科学 Blog

jasonkena.github.io·3d·Hacker News

Comp.compilers: Paper: MileStone: A Multi-Objective Compiler Phase Ordering Framework for Graph-based IR-Level Optimization 🤖机器学习

compilers.iecc.com·1d

Frontier Tuning: Teaching AI to work the way you do 🗂️知识管理 Blog

devblogs.microsoft.com·4d

Training an Agentic Router for Optimal Cost-Performance on SWE Tasks 👁️计算机视觉

appliedcompute.com·2d·Hacker News

Location: London, UK Remote: Yes Willing to relocate: Yes Technologies: Python, ... 🤖人工智能 Discussion

news.ycombinator.com·5d·Hacker News

AI alone won’t change your business. The system running it will. 👁️计算机视觉 Blog

blogs.microsoft.com·4d

What is MBPO? A Beginner’s Guide to Efficient Reinforcement Learning 👁️计算机视觉 Blog

ujangriswanto08.medium.com·1d

A Functional Taxonomy of World Models 🤖机器学习

Log in to enable infinite scrolling