Zeynep Akata

12

Papers

84

Total Citations

Papers (12)

DataDream: Few-shot Guided Dataset Generation

Scalable Ranked Preference Optimization for Text-to-Image Generation

EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval

Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training

Decoupling Angles and Strength in Low-rank Adaptation

SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutions

ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections

FLAIR: VLM with Fine-grained Language-informed Image Representations

How to Merge Your Multimodal Models Over Time?

Concept-Guided Interpretability via Neural Chunking

NeurIPS 2025arXiv

Context-Aware Multimodal Pretraining