Anna Rohrbach

Full Professor@Technische Universität Darmstadt·德国·OpenReview

研究方向

text2image generation · multimodal fact checking · image captioning · video description · explainable AI · textual explanations · Hallucination in MLLMs · visual grounding · visual question answering · Multimodal learning

2.5

Erased but Not Forgotten: How Backdoors Compromise Concept Erasure

ICLR 2026Withdrawn

通讯

7.8

Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detection

NeurIPS 2025Poster

6.7

When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning

COLM 2025Poster

通讯

5.8

Multi-domain Analysis and Generalization of Image manipulation loCalization

ICLR 2025Rejected

4.4

DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts

合作者 (18)