Damiano Marsili

I'm a Ph.D student at Caltech advised by Georgia Gkioxari and Pietro Perona. Before my Ph.D, I was an Applied Science Intern at Amazon Robotics working on 3D spatial reasoning. Prior to that, I double-majored at Johns Hopkins in Computer Science and Mathematics.

I'm interested in pushing the reasoning capabilities of multimodal LLMs. Most of my research involves post-training vision-language models for visual reasoning.

I'm best reachable via email at dmarsili at caltech dot edu.

Email Resume Google Scholar Twitter/X LinkedIn Github

01 / 03

News

May. 2026 I received the Outstanding Reviewer award for CVPR 2026 and the Gold Reviewer award from ICML 2026!
Feb. 2026 TWIN was accepted to CVPR 2026 as a Highlight✨!
Jan. 2026 VALOR was accepted to ICLR 2026!
Feb. 2025 VADAR was accepted to CVPR 2025!

02 / 03

Publications

TWIN project visual preview

CVPR Highlight✨2026

TWIN - Same or Not? Enhancing Visual Perception in Vision-Language Models

Damiano Marsili, Aditya Mehta, Ryan Lin, Georgia Gkioxari

project page arXiv code bibtex

ICLR2026

VALOR - No Labels, No Problem: Training Visual Reasoners with Multimodal Verifiers

Damiano Marsili, Georgia Gkioxari

project page arXiv code bibtex

CVPR2025

VADAR - Visual Agentic AI for Spatial Reasoning with a Dynamic API

Damiano Marsili*, Rohun Agrawal*, Yisong Yue, Georgia Gkioxari

project page arXiv code bibtex

03 / 03

Academic Services

Reviewer

CVPR (Outstanding Reviewer 2026), ICML (Gold Reviewer 2026), ECCV, NeurIPS, COLM

Workshop Reviewer

MUSI (CVPR 2026)

Teaching Assistant