Lin Guan Profile
Lin Guan

@GuanSuns

Followers
54
Following
35
Media
10
Statuses
35

Research  Scientist at Meta GenAI | PhD@ASU, BS@UT Austin | Building intelligent agents by learning from human feedback and harnessing large pre-trained models

Joined February 2017
Don't wanna be here? Send us removal request.
@rao2z
Subbarao Kambhampati (కంభంపాటి సుబ్బారావు)
1 year
📢 Yochanite Lin Guan (@GuanSuns; https://t.co/o8dAhpHaJo), 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
38
@GuanSuns
Lin Guan
1 year
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
4
16
@GuanSuns
Lin Guan
2 years
This work is also part of an ongoing effort in our lab (supervised by @rao2z ) to identify constructive roles that LLMs/VLMs can serve in planning tasks. 👉 Relevant paper:
Tweet card summary image
arxiv.org
There is considerable confusion about the role of Large Language Models (LLMs) in planning and reasoning tasks. On one side are over-optimistic claims that LLMs can indeed do these tasks with just...
0
0
1
@GuanSuns
Lin Guan
2 years
Our experiment also unveils the weakness of VLM critics — GPT-4V's critiques contain a considerable amount of hallucinated information, mainly due to limited visual-grounding capability. In the paper, we discussed how to mitigate this with extra "grounding feedback"
1
0
1
@GuanSuns
Lin Guan
2 years
To understand the capability and failure mode of VLM "style" critics, we collected a video benchmark that encompasses diverse behaviors which are goal-reaching but undesirable. We show that GPT-4V can identify a significant portion of undesirability (high recall rate)
1
0
1
@GuanSuns
Lin Guan
2 years
While LLMs cannot verify the correctness of agent behaviors, they can be good at capturing the "style" of desirable behaviors. We set out to find the effectiveness of VLM critics of undesirable behaviors.
1
1
14
@YantianZha
Yantian Zha
2 years
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
9
@rao2z
Subbarao Kambhampati (కంభంపాటి సుబ్బారావు)
2 years
📢📢 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
1
8
23
@rao2z
Subbarao Kambhampati (కంభంపాటి సుబ్బారావు)
2 years
📣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 👉 https://t.co/oiWYEhuWdV. We are told that ~300 folks signed up already..😱). w/ @karthikv792 @GuanSuns
0
7
42
@GuanSuns
Lin Guan
2 years
📢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: https://t.co/uT8KNkuv3y Presentation at NeurIPS 2023:
0
0
0
@GuanSuns
Lin Guan
2 years
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
0
4
@GuanSuns
Lin Guan
2 years
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/
0
0
1
@rao2z
Subbarao Kambhampati (కంభంపాటి సుబ్బారావు)
2 years
📢📢 Our #ICAPS2023 tutorial "On the role of Large Language Models in Planning"--all 3 hours of it--presented at @ICAPSConference in Praha this Monday, is now online. 👉 https://t.co/sS5gnxuy9g If you want to know whether or not LLMs can plan, this is just the ticket.. 1/
2
16
71
@rao2z
Subbarao Kambhampati (కంభంపాటి సుబ్బారావు)
3 years
📢 Although LLMs suck at the search needed to generate executable plans, they do have some approx. planning knowledge . Can we tease this out as world/domain models, and use them to drive planning? (w/ @GuanSuns, @karthikv792 & @sarath_ssreedh) 1/ 👉 https://t.co/aAK92sNl2B
1
10
26
@rao2z
Subbarao Kambhampati (కంభంపాటి సుబ్బారావు)
3 years
Move over Savanna 🐘 and Forest 🐘! Our #ICLR2023 paper brings in a brand new 🐘 to Rwanda : The RLHF 🐘 👇
@GuanSuns
Lin Guan
3 years
In our #ICLR2023 paper, we acknowledge the 🐘 in the RLHF room: By limiting humans to communicate their preferences only through 👍👎 on trajectories, RLHF is unbearably inefficient. Human preferences can be expressed in richer quasi-symbolic ways even for tacit knowledge tasks!
0
2
6
@GuanSuns
Lin Guan
3 years
Paper homepage: https://t.co/OjvGU86tBY Presentation at ICLR:
0
1
1
@GuanSuns
Lin Guan
3 years
Our ICLR 2023 paper (with @karthikv792 and @rao2z) enables users to control agents through relative attributes like bigger step size in tasks that involve both tacit and explicit knowledge. We achieve this by conditioning preference-based reward on quasi-symbolic **concepts**
1
1
2