Fiona Ryan
@fionakryan
Followers
1K
Following
2K
Media
24
Statuses
262
Computer Science PhD student @GeorgiaTech and NSF Graduate Research Fellow interested in understanding human behavior with computer vision
Atlanta, GA
Joined August 2018
RT @ngailapdi: #ICCV2025 3D VQA from multi-view RGBs? Hold my Gaussian 🎨.We present a generalizable 3DGS-Language framework for 3D visual Q….
0
3
0
There is 1 more week to submit non-archival extended abstracts to present at the Artificial Social Intelligence workshop @ICCVConference! We welcome work recently published in other venues (including the main ICCV conference) as well as works in progress!.
Excited to announce the Artificial Social Intelligence Workshop @ ICCV 2025 @ICCVConference. Join us in October to discuss the science of social intelligence and algorithms to advance socially-intelligent AI! Discussion will focus on reasoning, multimodality, and embodiment.
0
7
22
RT @ChengleiSi: Are AI scientists already better than human researchers?. We recruited 43 PhD students to spend 3 months executing research….
0
181
0
Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders [Sun PM #258]. TL;DR: a simple & effective framework for estimating gaze targets from a frozen, pretrained visual representation (DINOv2). paper: code:
1
1
8
Improving Personalized Search with Regularized Low-Rank Parameter Updates [Sat PM #376]. TL;DR: efficiently adapting CLIP for retrieving new concepts by representing them as low-rank param updates. paper: code:
1
0
3
I am at CVPR presenting 2 highlight papers on gaze target estimation and personalized vision-language retrieval this afternoon and tomorrow afternoon (see below for details and poster numbers 🧵) Come by and say hi!.
1
2
21
thanks for sharing our work! come talk with us at the Sunday PM poster session :).
CVPR 2025 papers pt. 1 - Gaze-LLE. Gaze-LLE simplifies gaze target estimation by building on top of a frozen DINOv2 visual foundation model; SOTA performance; open source code and model. more papers: ↓ more
1
3
65
RT @lmathur_: Future AI systems interacting with humans will need to perform social reasoning that is grounded in behavioral cues and exter….
0
16
0
We are very excited to host the Artificial Social Intelligence Workshop at #ICCV2025! We hope you'll join us there and consider submitting your work as a paper or extended abstract!.
Excited to announce the Artificial Social Intelligence Workshop @ ICCV 2025 @ICCVConference. Join us in October to discuss the science of social intelligence and algorithms to advance socially-intelligent AI! Discussion will focus on reasoning, multimodality, and embodiment.
0
4
17
RT @RickyTQChen: This ICLR is the best conference ever. Attendees are extremely friendly and cuddly. What do you mean this is the wrong….
0
30
0
RT @gtcomputing: A new approach for easily merging data models is bringing adaptable, multi-tasking #AIs closer to reality. A @GeorgiaTech….
0
4
0
RT @bryanislucky: 📢#CVPR2025 Introducing InstaManip, a novel multimodal autoregressive model for few-shot image editing. 🎯InstaManip can l….
0
5
0
RT @sstj389: Extracting structure that’s implicitly learned by video foundation models _without_ relying on labeled data is a fundamental c….
0
9
0
RT @Diyi_Yang: Check out 🔥 EgoNormia: a benchmark for physical social norm understanding Can we really trust VLMs….
0
37
0
RT @boztank: The first generation of Aria glasses have made a big impact in the research community, can't wait to see all the new possibili….
meta.com
Today, we're excited to announce the next step in the Project Aria journey: the introduction of Aria Gen 2 research glasses.
0
78
0