Shen Li

Postdoc @MIT & @MIT_CSAIL | Human-Robot/AI Interaction | Learning from Human Feedback

[Shen Li @ShenLiRobot]

✨ I’ll be at #NeurIPS2024 this week and happy to connect and chat!

[Shen Li @ShenLiRobot]

🚀 Excited to share: I'm on the academic job market this year! My research bridges psychology, robotics, and ML to personalize robot/AI assistance through human feedback by:
1️⃣ Modeling human cognition & behavior;
2️⃣ Developing ML & control algorithms for personalized assistance.

[Shen Li @ShenLiRobot]

Excited to present our #NeurIPS2024 Oral talk! 🚀

Enhancing Preference-based Linear Bandits via Human Response Time
Coffee or tea? If you choose instantly, you likely have a strong preference. How can AI leverage this psychological insight to better learn human preferences?

Curious? Don't think too long! Let's connect and explore how psychology drives smarter AI.

📅 Dec. 11, 3:30-3:50 PM PST
📍 Oral Session 2A: Agents (East Ballroom A, B)

👉 Conference Session https://t.co/0eiinUqcSL
👉 Paper on arXiv https://t.co/lHUWfpYWqy

[Shen Li @ShenLiRobot]

Excited to present our #NeurIPS2024 Oral talk! 🚀

Enhancing Preference-based Linear Bandits via Human Response Time
Coffee or tea? If you choose instantly, you likely have a strong preference. How can AI leverage this psychological insight to better learn human preferences?

Curious? Don't think too long! Let's connect and explore how psychology drives smarter AI.

📅 Dec. 11, 3:30-3:50 PM PST
📍 Oral Session 2A: Agents (East Ballroom A, B)

👉 Conference Session https://t.co/0eiinUqcSL
👉 Paper on arXiv https://t.co/lHUWfpYWqy

[Shen Li @ShenLiRobot]

Excited to share our new work: Enhancing Preference-based Linear Bandits via Human Response Time ⏱️🤖
@edgeyyzhang, Zhaolin Ren, Prof. Na Li, @ClaireYLiang, Prof. @julie_a_shah
👉 https://t.co/16IjLIXnkv

We show that human response times provide information about human preference strength, and speed up preference learning. This complements existing bandit algorithms that only learn from binary choices. We demonstrate this by integrating a psychology model (the EZ-Diffusion Model) into a bandit algorithm.

#AI #MachineLearning #RLHF #HumanFeedback #psychology #Bandits #Robotics #EZDiffusionModel

[Shen Li @ShenLiRobot]

Excited to share our new work: Enhancing Preference-based Linear Bandits via Human Response Time ⏱️🤖
@edgeyyzhang, Zhaolin Ren, Prof. Na Li, @ClaireYLiang, Prof. @julie_a_shah
👉 https://t.co/16IjLIXnkv

We show that human response times provide information about human preference strength, and speed up preference learning. This complements existing bandit algorithms that only learn from binary choices. We demonstrate this by integrating a psychology model (the EZ-Diffusion Model) into a bandit algorithm.

#AI #MachineLearning #RLHF #HumanFeedback #psychology #Bandits #Robotics #EZDiffusionModel