Minghao Yan (@Minghao__Yan) header
Minghao Yan (@Minghao__Yan) profile picture
Joined February 2019
Photo by Minghao Yan (@Minghao__Yan)Photo by Minghao Yan (@Minghao__Yan)Photo by Minghao Yan (@Minghao__Yan)Photo by Minghao Yan (@Minghao__Yan)Photo by Minghao Yan (@Minghao__Yan)Photo by Minghao Yan (@Minghao__Yan)Photo by Minghao Yan (@Minghao__Yan)Photo by Minghao Yan (@Minghao__Yan)Photo by Minghao Yan (@Minghao__Yan)Photo by Minghao Yan (@Minghao__Yan)
Minghao Yan retweeted
🤔 Is score centering (SC) all we need for stable async RL? People often stack truncated importance sampling (TIS) or KL penalties on top of SC. In a fun side project, we tested how much they help. We found that SC alone often matched on-policy. But when it fell short, adding more corrections doesn't necessarily help. 🧵
6
40
8
241
27,983
Check it out!!
I’ll be at @COLM_conf this week (Oct 5–10), presenting work from my internship at ByteDance Seed: “Towards Full Pipeline FP8 Reinforcement Learning for LLMs” arxiv.org/abs/2609.22870 Happy to chat about RL infra, agentic RL, and continual learning. Come say hi if you’re around :)
222
🚀🚀🚀
Scientific American has named ODBI’s Kaiyi Jiang to its inaugural list of Young American Scientists. Congrats, @idmjky! Jiang will join ODBI next month. Read more on the ODBI site: bioengineering.princeton.edu…
2
478
Minghao Yan retweeted
1/8) Excited to share PR²: Predictive Routing Replay for MoE-Based LLM RL! 🎉 This is also the first paper from our research group at @RutgersCS @RutgersU. While MoE LLMs scale remarkably well, RL training exposes a hidden source of instability: routing. Paper: arxiv.org/abs/2606.00395 A special shout-out to my talented PhD student, @DaizeDongCS, for leading this project and driving many of its key ideas and experiments.
3
12
2
31
4,453
Spot on! One of my biggest takeaways after working on AI scientists for a while.
Being good at next word prediction is the opposite of what we want for creativity, for scientific breakthroughs.
2
19
5,865
🚀 Thrilled to introduce PACEvolve: Enabling Long-Horizon Progress-Aware Consistent Evolution. We show how to push LLM self-evolution beyond short, unstable improvements and into consistent, long-horizon gains. 🧵👇
1
8
1
27
2,831
This work was done during my internship at Google and would not have been possible without my mentors and collaborators across Google and DeepMind. Kudos to everyone involved! Paper: arxiv.org/pdf/2601.10657 Code drop coming soon, stay tuned!
1
3
250
Our code is finally out at github.com/Google/pacevolve. Run it with your favorite task and see if you can push the scientific frontier!
🚀 Thrilled to introduce PACEvolve: Enabling Long-Horizon Progress-Aware Consistent Evolution. We show how to push LLM self-evolution beyond short, unstable improvements and into consistent, long-horizon gains. 🧵👇
1
4
490
Minghao Yan retweeted
All I want for Christmas is a new Matt Lakeman blogpost
1
1
7
1,895
I will be presenting our work, Decoding Speculative Decoding, at @naacl tomorrow. We identified the performance bottleneck in speculative decoding to be draft model depth and demonstrated low correlation between language modeling performance and token acceptance rate.
1
2
11
988
We showed that even for LLaMA 3.1 models, which were directly distilled from the target model, our lightweight method can still improve throughput by 52% with less than 10 minutes of distillation.
1
297
For more details, check out our paper and open-sourced draft models here, or catch me in person at the conference!
200