Matthias Hein

Full Professor, University of Tübingen

2 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 2

1 paper

Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Robustness in Both Domains: CLIP Needs a Robust Text Encoder

#3918 · Elias Abad Rocamora, Christian Schlarmann, Naman Deep Singh, Yongtao Wu, Matthias Hein, Volkan Cevher

We propose an efficient strategy for adversarial finetuning of the CLIP text encoder, enabling robustness in zero-shot classification, text-to-image retrieval and text-to-image generation.

Poster Session 4

1 paper

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning

#4708 · Amit Peleg, Naman Deep Singh, Matthias Hein

A fine-tuning method for Compositionally-aware Learning in CLIP