On-policy distillation provides an elegant way to use the teacher model as a process reward model to... - 惯性聚合

推荐订阅源

Proofpoint News Feed

The Last Watchdog

Secure Thoughts

cs.AI updates on arXiv.org

News | PayPal Newsroom

Application and Cybersecurity Blog

Security @ Cisco Blogs

宝玉的分享

Hacker News: Ask HN

Troy Hunt's Blog

Google Online Security Blog

WordPress大学

有赞技术团队

TaoSecurity Blog

Help Net Security

Security Affairs

博客园_首页

CXSECURITY Database RSS Feed - CXSecurity.com

博客园 - 聂微东

www.infosecurity-magazine.com

Recent Announcements

Privacy & Cybersecurity Law Blog

cs.CV updates on arXiv.org

Hugging Face - Blog

博客园 - 司徒正美

Google DeepMind News

Schneier on Security

Recent Commits to openclaw:main

The Exploit Database - CXSecurity.com

LINUX DO - 热门话题

CTFtime.org: upcoming CTF events

News and Events Feed by Topic

LINUX DO - 最新话题

Full Disclosure

大猫的无限游戏

Heimdal Security Blog

SegmentFault 最新的问题

Lilian Weng(@lilianweng)

new post on harness engineering for AI self-improvement: https://t.co/ZYvGfVs61k It is hard to fore... Soon I should set up the model to update Lil’Log automatically but I’m not there yet. I wonder how many more people will just ask model to summarize the post, in comparison to a year ago... A super long overdue (3+ years?) post on scaling laws. Compute is expensive. Scaling laws are a way... We would love to see more collaboration and research in the field of human-AI interactivity. Check i... I only recently read more about the concept of system accidents by Charles Perrow, very insightful a... In the past few months, we had a lot of fun (and stress 😅) to produce 12 versions (+ many subversio... Building technologies for better human-AI collaboration on next gen hardware at scale. Exciting. I’ve been telling people this a lot today: I enjoy so much working with people who care about what t... GPUs are expensive and setting up the infrastructure to make GPUs work for you properly is complex, ... Looking through those little hidden gem stories in the footnote, you will find it so inspiring that ... To be clear, here the (first) Thinking Machines Corporation (https://t.co/DTcUwSNI6C) I referred to ... Besides the fun fact that Connectionism is connected with the early days of the AI field and highlig... Welcome @_kevinlu to the team! Exciting to work together again. Yes - 🥳 Thinky starts hiring again: https://t.co/Dy97oJHbxy I still find it mysterious whether and how intelligence and capabilities transfer between domains an... Probably the first product Thinky will build is a full panel of dials that researchers can use to ph... Giving your models more time to think before prediction, like via smart decoding, chain-of-thoughts ... When a new dataset comes out, I get excited and check it out and then only realize that this is anot... Nope what’s that? See you at #ICLR2025 soon. Excited about chatting with many of you about Thinking Machines and what ... 👩‍🍳Actively cooking the next blog post. Tiny teaser: It is spiritually related to our new company... Rule-based rewards (RBRs) use model to provide RL signals based on a set of safety rubrics, making i... Rebirth About 650 / 770 signed at this moment. As people start waking up, more will come. All the efforts st... (1/3) Alongside Superalignment team, my team is working on the practical side of alignment: Building... Check out this post with @gdb, if you are curious about how to train large deep learning models and ...

On-policy distillation provides an elegant way to use the teacher model as a process reward model to...

Lilian Weng · 2025-10-28 · via Lilian Weng(@lilianweng)

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。原文来自 — 版权归原作者所有。