Ivana Kajić

5 papers · 2019–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (12) 🐣 Hot Topic Early Bird ❓ The Questioner

Venues

NeurIPS (2) EACL (1) ICCV (1) ICLR (1)

Top co-authors

Aida Nematzadeh (3) Jordi Pont-Tuset (2) Emanuele Bugliarello (2) Su Wang (2) Isabela Albuquerque (2) Olivia Wiles (2) Ahmed Imtiaz Humayun (1) Phil Blunsom (1) Najoung Kim (1) Chris Eliasmith (1)

Research topics

Artificial Intelligence (5) Core AI (5) Deep Learning (4) Models (3) Machine Learning (2) Optimization & Theory (2) Application Areas (1) Architectures (1) Core Methods (1)

Keywords

generative model (3) text-to-image generation (2) multimodal learning (2) model safety (1) out-of-distribution generalization (1) object counting (1) recurrent neural network (1) text-to-image model (1) vision-language model (1) evaluation metric (1) ordinary differential equation (1) multimodal model (1) concept erasure (1) prompt alignment (1) human annotation (1) long-term dependency (1) numerical reasoning (1) cross-dataset evaluation (1) continuous-time representation (1) legendre memory unit (1)

Papers

Erasing More Than Intended? How Concept Erasure Degrades the Generation of Non-Target Concepts ICCV 2025 Revisiting text-to-image evaluation with Gecko: on metrics, prompts, and human rating ICLR 2025 Evaluating Numerical Reasoning in Text-to-Image Models NeurIPS 2024 Reassessing Evaluation Practices in Visual Question Answering: A Case Study on Out-of-Distribution Generalization EACL 2023 Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks NeurIPS 2019