Hi, I'm Gabe Sarch

I'm a fourth-year Ph.D. student at Carnegie Mellon University in the Neural Computation and Machine Learning joint PhD program under the supervision of Dr. Katerina Fragkiadaki and Dr. Mike Tarr. My work is supported by the National Science Foundation Graduate Research Fellowship. Previously, I received a B.S. in Biomedical Engineering from the University of Rochester, where I studied the marmoset visual system under Dr. Jude Mitchell.

I am interning at Microsoft Research during Summer 2024, mentored by Andrew Wilson and Bala Kumaravel.

profile photo




Research


VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought

GH SarchL JangMJ TarrK MarinoW CohenK Fragkiadaki
Neurips Spotlight


Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models

GH SarchY WuMJ TarrK Fragkiadaki
EMNLP Findings 2023
🔥[NEW!] in ICLR 2024 Workshop on LLM Agents: HELPER-X achieves Few-Shot SoTA on 4 embodied AI benchmarks (ALFRED, TEACh, DialFRED, and the Tidy Task) using a single agent, with just simple modifications to the original HELPER.


Brain Dissection: fMRI-trained Networks Reveal Spatial Selectivity in the Processing of Natural Images

GH SarchMJ TarrK Fragkiadaki*L Wehbe*
*equal advising
NeurIPS 2023


3D View Prediction Models of the Dorsal Visual Stream

GH SarchHF TungA WangJS PrinceMJ Tarr
CCN 2023


TIDEE: Tidying Up Novel Rooms using Visuo-Semantic Commonsense Priors

2023 CVPR Embodied AI Rearrangement Challenge winner
GH SarchZ FangAW HarleyP SchydloMJ TarrS GuptaK Fragkiadaki
ECCV 2022


Beyond Fixation: detailed characterization of neural selectivity in free-viewing primates

JL YatesSH CoopGH SarchR WuD ButtsM Rucci Jude Mitchell
Nature Communications


Move to See Better: Towards Self-Improving Embodied Object Detection

GH Sarch*Z Fang*A Jain*AW Harley K Fragkiadaki
*equal contribution
BMVC 2021


See all my publications