Manuel Cherep
@mcherep.bsky.social
PhD student at MIT working on behavioral machine learning.
🚨New Preprint 🚨
Current agent evals mostly measure competence, but miss behavior e.g. are their decisions stable, rational, manipulable, human-like?
We introduce ABxLAB, a framework for studying agent behavior. Using it we create an agentic consumer behavior benchmark.
🧵1/9
Current agent evals mostly measure competence, but miss behavior e.g. are their decisions stable, rational, manipulable, human-like?
We introduce ABxLAB, a framework for studying agent behavior. Using it we create an agentic consumer behavior benchmark.
🧵1/9
October 23, 2025 at 6:16 PM
🚨New Preprint 🚨
Current agent evals mostly measure competence, but miss behavior e.g. are their decisions stable, rational, manipulable, human-like?
We introduce ABxLAB, a framework for studying agent behavior. Using it we create an agentic consumer behavior benchmark.
🧵1/9
Current agent evals mostly measure competence, but miss behavior e.g. are their decisions stable, rational, manipulable, human-like?
We introduce ABxLAB, a framework for studying agent behavior. Using it we create an agentic consumer behavior benchmark.
🧵1/9
✨Contrastive Learning from Synthetic Audio Doppelgängers #ICLR2025✨ w/
@nikhilsinghmus.bsky.social
Our method learns useful audio representations with randomly synthesized sounds (often better than real data!)
🌐Project: doppelgangers.media.mit.edu
📄Paper: arxiv.org/abs/2406.05923
🧵1/3
@nikhilsinghmus.bsky.social
Our method learns useful audio representations with randomly synthesized sounds (often better than real data!)
🌐Project: doppelgangers.media.mit.edu
📄Paper: arxiv.org/abs/2406.05923
🧵1/3
March 12, 2025 at 8:25 PM
✨Contrastive Learning from Synthetic Audio Doppelgängers #ICLR2025✨ w/
@nikhilsinghmus.bsky.social
Our method learns useful audio representations with randomly synthesized sounds (often better than real data!)
🌐Project: doppelgangers.media.mit.edu
📄Paper: arxiv.org/abs/2406.05923
🧵1/3
@nikhilsinghmus.bsky.social
Our method learns useful audio representations with randomly synthesized sounds (often better than real data!)
🌐Project: doppelgangers.media.mit.edu
📄Paper: arxiv.org/abs/2406.05923
🧵1/3
Excited to present our new paper on nudging LLMs (👉🤖) as a spotlight talk at the NeurIPS Behavioral ML Workshop! @neuripsconf.bsky.social
w/ Nikhil Singh* (@nikhilsinghmus.bsky.social) and Pattie Maes
🔗 openreview.net/forum?id=chb...
🧵 1/3
w/ Nikhil Singh* (@nikhilsinghmus.bsky.social) and Pattie Maes
🔗 openreview.net/forum?id=chb...
🧵 1/3
November 26, 2024 at 11:07 PM
Excited to present our new paper on nudging LLMs (👉🤖) as a spotlight talk at the NeurIPS Behavioral ML Workshop! @neuripsconf.bsky.social
w/ Nikhil Singh* (@nikhilsinghmus.bsky.social) and Pattie Maes
🔗 openreview.net/forum?id=chb...
🧵 1/3
w/ Nikhil Singh* (@nikhilsinghmus.bsky.social) and Pattie Maes
🔗 openreview.net/forum?id=chb...
🧵 1/3