Andi Peng

Learning How Hard to Think: Input-Adaptive Allocation of LM Computation

Thu, 10 Oct 2024 00:00:00 +0000

Adaptive Language-Guided Abstraction from Contrastive Explanations

Sat, 08 Jun 2024 00:00:00 +0000

Constrained Human-AI: An Inclusive Embodied AI Assistance Challenge

Sun, 19 May 2024 00:00:00 +0000

Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Feedback

Tue, 30 Jan 2024 00:00:00 +0000

Learning with Language-Guided State Abstractions

Tue, 16 Jan 2024 00:00:00 +0000

Aligning Robot Representations with Humans

Thu, 30 Nov 2023 00:00:00 +0000

Preference-Conditioned Language-Guided Abstractions

Thu, 30 Nov 2023 00:00:00 +0000

Getting Aligned on Representational Alignment

Wed, 01 Nov 2023 00:00:00 +0000

Human-Guided Complexity-Controlled Abstractions

Wed, 23 Aug 2023 00:00:00 +0000

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

Tue, 23 May 2023 00:00:00 +0000

Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation

Thu, 23 Feb 2023 00:00:00 +0000

Strengthening Subcommunities: Towards Sustainable Growth in AI Research

Thu, 21 Apr 2022 00:00:00 +0000

Make Greenhouse-Gas Accounting Reliable — Build Interoperable Systems

Tue, 12 Apr 2022 00:00:00 +0000

Investigations of Performance and Bias in Human-AI Teamwork in Hiring

Tue, 22 Feb 2022 00:00:00 +0000

On the Nature of Bias Percolation: Assessing Multiaxial Collaboration in Human-AI Systems

Sun, 26 Apr 2020 00:00:00 +0000

Human-Machine Collaboration for Fast Land Cover Mapping

Fri, 07 Feb 2020 00:00:00 +0000

The Perils of Objectivity: Towards a Normative Framework for Fair Judicial Decision-Making

Fri, 07 Feb 2020 00:00:00 +0000

What You See Is What You Get? The Impact of Representation Criteria on Human Bias in Hiring

Mon, 28 Oct 2019 00:00:00 +0000

Artificial Intelligence Research and Ethics Community Calls for Standards in Criminal Justice Risk Assessment Tools

Fri, 26 Apr 2019 00:00:00 +0000

My Journey to the Microsoft Research AI Residency

Mon, 10 Sep 2018 00:00:00 +0000

An Integrated Machine Learning Approach To Studying Terrorism

Fri, 20 Apr 2018 00:00:00 +0000

News

Fri, 01 Dec 2017 00:00:00 +0000

[Nov 2024] Attending CoRL! I’ll be presenting Adaptive Language-Guided Abstraction from Contrastive Explanations in the main conference.

[Aug 2024] I am taking leave from MIT to lead national security evaluations on the Frontier Red Team at Anthropic.

[Aug 2024] Attending RLC! I’ll be presenting Pragmatic Feature Preferences in the RL Beyond Rewards Workshop.

[Jul 2024] Attending ICML! I’ll be presenting Pragmatic Feature Preferences in the main conference. I’ll also be attending the Alignment Workshop beforehand.

[Jul 2024] Attending RSS! I’m honored to be part of the 2024 RSS Pioneers cohort, as well as help organize the Social Intelligence in Humans and Robots Workshop and the Task Specification Workshop.

[May 2024] I started at Anthropic! I’ll be working to help make big models safer.

[May 2024] Attending ICLR! I’ll be presenting LGA in the main conference and PLGA in the LLM Agents Workshop. I’ll also be a panelist in the Representational Alignment Workshop.

[Apr 2024] I ran the Boston Marathon!

[Mar 2024] Attending HRI! Our papers Aligning Human and Robot Representations and Preference-Conditioned Language-Guided Abstraction will be presented in the main conference.

[Feb 2024] I am giving talks at the MILA Robot Learning Seminar and UC Berkeley.

[Feb 2024] I will be visiting Constellation, an AI safety research center, for two weeks!

[Jan 2024] Our paper Learning with Language-Guided State Abstractions was accepted to ICLR 2024.

[Dec 2023] Attending NeurIPS! I’m presenting Human-Guided Complexity-Controlled Abstractions in the main conference and co-organizing the Goal-Conditioned Reinforcement Learning Workshop.

[Nov 2023] Our paper Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback was accepted to TMLR.

[Nov 2023] Our papers Aligning Human and Robot Representations and Preference-Conditioned Language-Guided Abstraction were accepted to HRI 2024.

[Nov 2023] Our new preprint Getting Aligned on Representational Alignment is out.

[Nov 2023] I passed my quals at MIT!

[Sep 2023] Our paper Human-Guided Complexity-Controlled Abstractions was accepted to NeurIPS 2023.

[Sep 2023] I started my internship at the Boston Dynamics AI Institute!

[Jul 2023] I gave an interview for The Inside View at ICML!

[Jul 2023] Attending ICML! I’m presenting Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation in the main conference and co-organizing the Interactive Learning from Implicit Human Feedback Workshop.

[Jun 2023] I started my internship at the MIT-IBM Watson AI Lab.

[May 2023] I spoke alongside Congressman Bill Foster at the Aon AI Fireside Chat.

[May 2023] I gave a talk at the Yale for Humanity event on Artificial Intelligence, Ethics, and Society: Utilizing Technology for Good.

[Apr 2023] Our paper Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation was accepted to ICML 2023.

[Apr 2023] I ran the Boston Marathon!

[Feb 2023] I was awarded a fellowship from Open Philanthropy!

[Feb 2023] I received my M.S. from MIT EECS.

[Dec 2022] I co-organized the Aligning Robot Representations with Humans workshop at CoRL 2022.

[Dec 2022] I presented two workshop papers at NeurIPS 2022.

[Jul 2022] Our paper Make greenhouse-gas accounting reliable — build interoperable systems was published in Nature.

[Feb 2022] I presented Investigations of Performance and Bias in Human-AI Teamwork in Hiring as an oral presentation at AAAI 2022.

[May 2021] I started my internship at FAIR.

[Sep 2020] I started my PhD at MIT advised by Pulkit Agrawal.

[Apr 2022] I was awarded the NSF GRFP fellowship.

Virgin Hyperloop One - Branson Boosts Elon Musk's Futuristic Tube Transport

Thu, 12 Oct 2017 00:00:00 +0000

Faster, cheaper, cleaner - Experts disagree about Elon Musk's Hyperloop claims

Fri, 04 Aug 2017 00:00:00 +0000

Three Yale students named Truman Scholars

Mon, 17 Apr 2017 00:00:00 +0000

Conceptual Feasibility Study of the Hyperloop Vehicle for Next-Generation Transport

Thu, 05 Jan 2017 00:00:00 +0000

Early Detection of Boko Haram Attacks in Nigeria

Wed, 21 Dec 2016 00:00:00 +0000