正在加载视频...

视频加载失败

1. Machine Learning Specialization. Break Into AI with this 3-course program by Andrew Ng. What You’ll learn: → Build ML models → Train neural networks → Deep reinforcement learning → Unsupervised learning techniques 🔗

364,444 次观看 • 1 年前 •via X (Twitter)

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

50 websites you’ll wish you knew sooner 👀 1. — Discover useful AI tools 2. — Find AI tools for almost anything 3. — Explore AI tools & apps 4. — Try community-built AI demos 5. — Run AI models online 6. — AI video & creative tools 7. — AI image generation 8. — Create images with strong text rendering 9. — Generate AI music 10. — AI voice generation 11. — Create presentations with AI 12. — Turn ideas into visual diagrams 13. — Collaborative online whiteboard 14. — Simple hand-drawn style diagrams 15. — Create diagrams & flowcharts 16. — Open-source design platform 17. — Generate color palettes 18. — Find font combinations 19. — Identify fonts from images 20. — Create favicons quickly 21. — Create QR codes 22. — Compress JPEG images 23. — Compress PNG & WebP images 24. — Convert files between formats 25. — Convert almost any file 26. — Edit & optimize images 27. — Create vector graphics online 28. — Free high-quality photography 29. — Free stock photos & videos 30. — Free images, videos & illustrations 31. — Free stock videos, music & templates 32. — Free stock videos for creative projects 33. — Build customizable human illustrations 34. — Free customizable illustrations 35. — Animated illustrations for projects 36. — Learn how sitemaps work 37. — Build & test regular expressions 38. — Format & validate JSON 39. — Decode and inspect JWT tokens 40. — Test & explore APIs 41. — Send HTTP requests online 42. — Create beautiful code screenshots 43. — Turn code into beautiful images 44. — Check JavaScript package sizes 45. — Developer roadmaps & learning paths 46. — Explore career roadmaps 47. — Discover visual learning paths 48. — Learn programming concepts quickly 49. — Cheat sheets for developers 50. — Explore aircraft & satellites flying over you in real time The internet isn’t just social media. There are thousands of tools quietly making work, learning, creativity and everyday life more interesting. 🔖 Bookmark this. You’ll thank yourself later. Follow Monica for more useful websites & AI tools.

Monica

57,661 次观看 • 7 天前

50 websites you’ll wish you knew sooner 👀 1. — Discover useful AI tools 2. — Find AI tools for almost anything 3. — Explore AI tools & apps 4. — Try community-built AI demos 5. — Run AI models online 6. — AI video & creative tools 7. — AI image generation 8. — Create images with strong text rendering 9. — Generate AI music 10. — AI voice generation 11. — Create presentations with AI 12. — Turn ideas into visual diagrams 13. — Collaborative online whiteboard 14. — Simple hand-drawn style diagrams 15. — Create diagrams & flowcharts 16. — Open-source design platform 17. — Generate color palettes 18. — Find font combinations 19. — Identify fonts from images 20. — Create favicons quickly 21. — Create QR codes 22. — Compress JPEG images 23. — Compress PNG & WebP images 24. — Convert files between formats 25. — Convert almost any file 26. — Edit & optimize images 27. — Create vector graphics online 28. — Free high-quality photography 29. — Free stock photos & videos 30. — Free images, videos & illustrations 31. — Free stock videos, music & templates 32. — Free stock videos for creative projects 33. — Build customizable human illustrations 34. — Free customizable illustrations 35. — Animated illustrations for projects 36. — Learn how sitemaps work 37. — Build & test regular expressions 38. — Format & validate JSON 39. — Decode and inspect JWT tokens 40. — Test & explore APIs 41. — Send HTTP requests online 42. — Create beautiful code screenshots 43. — Turn code into beautiful images 44. — Check JavaScript package sizes 45. — Developer roadmaps & learning paths 46. — Explore career roadmaps 47. — Discover visual learning paths 48. — Learn programming concepts quickly 49. — Cheat sheets for developers 50. — Explore aircraft & satellites flying over you in real time The internet isn’t just social media. There are thousands of tools quietly making work, learning, creativity and everyday life more interesting. 🔖 Bookmark this. You’ll thank yourself later. Follow Raya for more useful websites & AI tools.

Raya

44,709 次观看 • 5 天前

𝗗𝗼𝗻'𝘁 𝗳𝗶𝗻𝗲-𝘁𝘂𝗻𝗲 𝗿𝗼𝗯𝗼𝘁 𝗳𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 𝗺𝗼𝗱𝗲𝗹𝘀. 𝗦𝘁𝗲𝗲𝗿 𝘁𝗵𝗲𝗺 𝘄𝗶𝘁𝗵 𝗵𝘂𝗺𝗮𝗻 𝗰𝗼𝗿𝗿𝗲𝗰𝘁𝗶𝗼𝗻𝘀 𝗶𝗻𝘀𝘁𝗲𝗮𝗱, 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 𝗰𝗵𝗮𝗻𝗴𝗶𝗻𝗴 𝘁𝗵𝗲 𝗯𝗮𝘀𝗲 𝗽𝗼𝗹𝗶𝗰𝘆 Modern VLAs and world-action models can perform impressive manipulation skills, but adapting them reliably to new robots and tasks remains challenging. A natural solution is DAgger-style online imitation learning: deploy the robot, collect human corrections, and update the policy. Yet foundation models are fragile in the low-data regime, fine-tuning on a handful of interventions can improve one behavior while degrading others. Online post-training or reinforcement learning can require costly data collection and exploration, making real-world learning expensive and potentially unsafe. In our new paper, 𝗙𝗹𝗼𝘄𝗗𝗔𝗴𝗴𝗲𝗿, we take a different approach: 𝗜𝗻𝘀𝘁𝗲𝗮𝗱 𝗼𝗳 𝗰𝗵𝗮𝗻𝗴𝗶𝗻𝗴 𝘁𝗵𝗲 𝗳𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 𝗺𝗼𝗱𝗲𝗹, 𝘄𝗲 𝗹𝗲𝗮𝗿𝗻 𝗵𝗼𝘄 𝘁𝗼 𝘀𝘁𝗲𝗲𝗿 𝗶𝘁 𝗳𝗿𝗼𝗺 𝗵𝘂𝗺𝗮𝗻 𝗰𝗼𝗿𝗿𝗲𝗰𝘁𝗶𝗼𝗻𝘀. The key idea is 𝗮𝗰𝘁𝗶𝗼𝗻 𝗶𝗻𝘃𝗲𝗿𝘀𝗶𝗼𝗻: we map human corrective actions back into the latent noise space of the frozen generative policy. These latent targets train a lightweight controller that adapts the robot while preserving the original model's capabilities. Across simulation and real robots, FlowDAgger: 📈 Learns from only 5–20 human intervention episodes 🏆 Outperforms supervised fine-tuning and latent-space reinforcement learning 🤖 Works across VLAs, diffusion policies, and world-action models ✔️ Provides reliable improvements without modifying the pretrained policy We believe this offers a practical path toward making robot foundation models improve during deployment, learning from the way humans naturally teach: through corrections. 📄 Paper: 🌐 Project: 💻 Code: This project was led by my amazing colleague Michael Murray with help from Daphne Chen, Simran Bagaria, Dean Fortier, Tess Hellebrekers, Harshavardhan Reddy Gajarla, Galen Mullins and Andrey Kolobov at Microsoft Research and Maya Cakmak at University of Washington

Oier Mees

13,233 次观看 • 1 个月前