Zeynep Akata

Center for Integrated Protein Science Munich — Germany

Computer Science · Physical Sciences

47h-index16.2kcitations271works2.12yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Domain Adaptation and Few-Shot Learning(117), Multimodal Machine Learning Applications(112), Advanced Image and Video Retrieval Techniques(40), Advanced Neural Network Applications(36), Topic Modeling(32)

Publications271 total

A Systematic Study of Model Merging Techniques in Large Language Models
arXiv (Cornell University)·2025Open Access
Sparse Autoencoders are Topic Models
arXiv (Cornell University)·2025Open Access
Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models
arXiv (Cornell University)·2025Open Access
Reference-Free Rating of LLM Responses via Latent Information
arXiv (Cornell University)·2025Open Access
Road Obstacle Video Segmentation
arXiv (Cornell University)·2025Open Access
SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutions
arXiv (Cornell University)·2025Open Access
Investigating Structural Pruning and Recovery Techniques for Compressing Multimodal Large Language Models: An Empirical Study
arXiv (Cornell University)·2025Open Access
Align-then-Unlearn: Embedding Alignment for LLM Unlearning
arXiv (Cornell University)·2025Open Access
How to Merge Your Multimodal Models Over Time?
2025
Context-Aware Multimodal Pretraining
2025
FLAIR: VLM with Fine-grained Language-informed Image Representations
2025· 1 cited
COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
2025· 3 cited
Time Series Representations for Classification Lie Hidden in Pretrained Vision Transformers
arXiv (Cornell University)·2025Open Access
DD-Ranking: Rethinking the Evaluation of Dataset Distillation
arXiv (Cornell University)·2025Open Access
Concept-Guided Interpretability via Neural Chunking
arXiv (Cornell University)·2025Open Access
Feasibility with Language Models for Open-World Compositional Zero-Shot Learning
arXiv (Cornell University)·2025Open Access
LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance
arXiv (Cornell University)·2025Open Access
Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
arXiv (Cornell University)·2025Open Access
DeLoRA: Decoupling Angles and Strength in Low-rank Adaptation
arXiv (Cornell University)·2025Open Access
WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs
arXiv (Cornell University)·2025Open Access
page 1 of 14Next →

Frequent Co-authors

Bernt Schiele(22), Yongqin Xian(12), Trevor Darrell(8), Lisa Anne Hendricks(6), Scott Reed(5), Honglak Lee(5), Massimiliano Mancini(5), Florent Perronnin(4), Zaïd Harchaoui(4), Cordelia Schmid(4), Marcus Rohrbach(4), A. Sophia Koepke(4), Christoph H. Lampert(2), Xinchen Yan(2), Lajanugen Logeswaran(2), Matthias Hein(2), Jeff Donahue(2), Anna Rohrbach(2), Seong Joon Oh(2), Mario Fritz(2)