Lin Guan (@GuanSuns) profile picture

Research Scientist at Meta GenAI | PhD@ASU, BS@UT Austin | RL and planning for conversational models and agents.

Joined February 2017
Photo by Lin Guan (@GuanSuns)Photo by Lin Guan (@GuanSuns)Photo by Lin Guan (@GuanSuns)Photo by Lin Guan (@GuanSuns)Photo by Lin Guan (@GuanSuns)Photo by Lin Guan (@GuanSuns)Photo by Lin Guan (@GuanSuns)Photo by Lin Guan (@GuanSuns)Photo by Lin Guan (@GuanSuns)Photo by Lin Guan (@GuanSuns)
Our latest work demonstrates how industry-scale Flywheel systems can iteratively drive model improvements even when the objectives are not easily tractable!
1/5 🤔 LLMs can solve olympiad math and write production code. But can they hold a conversation that's actually fun — one that people want to keep coming back to? 💬✨ We present CharacterFlywheel— an iterative process optimizing LLMs for real human engagement and character steerability, while maintaining rigorous safety protocols 🔒. Tested across Instagram, WhatsApp & Messenger 📱with millions of users — where they can create, share, and chat with their own AI characters 🤖. 📄 paper: arxiv.org/abs/2603.01973 huggingface.co/papers/2603.0…
1
81
Our latest work sheds light on what to "scale" when building generalizable agents: 👉 Prefer training envs with 📚 high state information richness (high perception load & info volume) + 🧠high planning complexity (long task horizon & branching factors) 👉 The *complexity structure* matters more than realism: Hard problems in "toy" domains like Sokoban / BlocksWorld can be more useful than easy problems in more realistic domains like ALFWorld. ‼️📉 Be careful about your mid-training datamix and strength: warmup and mid-training help prevent catastrophic forgetting during RL but undermines generalization to domains that are not covered 💡Applying lightweight state randomization/augmentation helps! 📄 Paper: huggingface.co/papers/2601.1…
1
4
1
9
1,058
🤔 Motivation: Just like AlphaGo, given enough compute and proper configurations, RL agents can achieve superhuman performance in almost all training tasks ⚠️ However, LLM agents today are being used in tasks far beyond what limited post-training data can cover — a challenge highlighted by many researchers like @ilyasut, @MiniMax_AI (in platform.minimax.io/docs/gui…) and @Kimi_Moonshot in K2.5 tech report.
1
2
3
468
People are putting lots of efforts into building diverse RL environments. But what kinds of environments are more useful for building **generalist** agents that are able to solve tasks beyond their training tasks? 🚀 Instead of optimizing one single benchmark, we look for drivers of transfer in our latest paper: huggingface.co/papers/2601.1… Joint work with MSL @MetaAI (@ZhihanLiu21628 @GuanSuns @EasonNie @KaiZhang_CS @nazzhang) where @ZhihanLiu21628 interned. (1/n)
4
23
1
111
7,896
📢 Yochanite Lin Guan (@GuanSuns; guansuns.github.io/), currently a Research Scientist with @Meta GenAI, will be defending his @SCAI_ASU PhD dissertation tomorrow 10/21 👇. He developed several 🔥 techniques for taming the notorious sample complexity of #RL systems..
2
2
1
38
7,307
While LLMs cannot verify the correctness of agent plans, they can be good at capturing the "style" of desirable behaviors. Come stop by #COLM2024 poster #34 Wednesday Morning to see how we utilize VLMs as a knowledge source of common human preferences for embodied agents!
1
5
1
16
6,249
Robots now understand decisions via SERLfD – Self-Explanation for Reinforcement Learning from Demonstrations, transcending traditional robot learning from human demos. Check out our article and slides; find more insights at poster 409 during AAAI-24 on 2/23, 7-9 PM!🤖🌐 #AAAI2024
1
1
1
9
3,855
📢📢 Come stop by #AAAI2024 poster spots 644 & 645 (the very last spots) this evening to hear me explain the neat work of 👉@ZahraZ__ & @sailiks on explaining allocations to humans 👉@YantianZha & @GuanSuns on using self explanations to learn from ambiguous demonstrations [Note that at my request, the posters were placed in contiguous spots instead of their original spots 409/435 so I didn't have to master the art of being in two places at one time.. 😋]
1
8
2
22
13,187
📣Chalk it to mad masochism, but we will be updating and reprising our tutorial on LLMs and Planning at #AAAI2024 Vancouver, BC. (Wed Feb 21st, 2-6PM 👉aaai.org/aaai-conference/aaa…. We are told that ~300 folks signed up already..😱). w/ @karthikv792 @GuanSuns
7
1
41
39,339
Interested in building #LLMAgent but tired of endlessly fixing flawed plans? 😫🤦‍♀️ Our #NeurIPS paper reveals LLMs aren’t designed for action sequencing! Instead, they can be useful for extracting planning knowledge and generating codified models that drive external planners!💡1/
1
1
4
1,853
📢Don't miss out our poster session tomorrow (Dec 12) starting at 5:15 p.m. CST in the Great Hall & Hall B1+B2 #1525 This is a joint work with @karthikv792 @sarath_ssreedh and @rao2z Paper homepage: guansuns.github.io/pages/llm… Presentation at NeurIPS 2023: neurips.cc/virtual/2023/post…
205
Having missed attending #ICLR2023 in-person, we are also re-presenting the paper at the #ICML2023 ILHF workshop on Saturday, July 29th. Feel free to drop by if you are on Waikiki ... 🏖️ Mahalo 🙏 2/
1
93