🔒 Trustworthy FMs Workshop

Trust Before Use: Building Foundation Models that You Can Trust

📍 In conjunction with ICCV 2025 — Oct. 19–23, Honolulu, Hawai'i

Overview Schedule Accepeted Papers Call for Papers Invited Speakers Senior Organizers Organizers Attending

🗓 Schedule

ICCV 2025 Workshop Day 10/20 • Honolulu, Hawai'i • Afternoon Session

Time Session Speakers / Notes
1:00 - 1:10Opening RemarksWorkshop Start
1:10 - 1:40Session S1Prof. Shaoron Li
1:40 - 2:10Session S2Prof. Salman Avestimehr
2:10 - 2:20Oral Presentations IControlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning
2:20 - 2:30Oral Presentations IIDASH: Detection and Assessment of Systematic Hallucinations of VLMs
2:30 - 2:40Oral Presentations IIIGaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation
2:40 - 3:10Session S3Prof. Yao Qin
3:10 - 4:00Poster SessionInteractive discussion
4:00 - 4:30Session S4Dr. Chengzhi Mao
4:30 - 5:00Session S5Dr. Mazda Moayeri
5:10 - 5:20Oral Presentations IVRobust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models
5:20 - 5:30Oral Presentations VDoxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Model
5:30 - 5:40Invited Oral PresentationsHarnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability
5:40 - 5:50ClosingWrap-up