Papers by Moran Yanuka
Bridging the Visual Gap: Fine-Tuning Multimodal Models with Knowledge-Adapted Captions (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent work focuses on training vision-language models with long, detailed image captions, but small-scale VLMs struggle to balance the richness of these captions with the risk of hallucinations. |
| Approach: | They propose an evaluation framework that breaks down generated captions into individual propositions, assessing each in isolation. |
| Outcome: | The proposed framework outperforms baselines in both automatic metrics and human evaluations on small-scale vision-language models with long, detailed captions. |
EditInspector: A Benchmark for Evaluation of Text-Guided Image Edits (2025.acl-long)
Copied to clipboard
| Challenge: | Text-guided image editing is becoming increasingly widespread . current models struggle to evaluate edits comprehensively and often hallucinate when describing changes. |
| Approach: | They propose a novel framework to evaluate edits based on human annotations . they use a template to collect human annotation data and validate the results . |
| Outcome: | The proposed methods outperform current models in artifact detection and difference caption generation. |
ICC : Quantifying Image Caption Concreteness for Multimodal Dataset Curation (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to curation text-image data are noisy and lack the fine-grained ability to isolate the most concrete samples that provide the strongest signal for learning in a noisy dataset. |
| Approach: | They propose a metric that evaluates caption text without an image reference to measure its concreteness and relevancy. |
| Outcome: | The proposed method detects the concreteness of captions without an image reference and correlates with human evaluation of concreteness in both single-word and caption-level texts. |
ConlangCrafter: Constructing Languages with a Multi-Hop LLM Pipeline (2026.acl-long)
Copied to clipboard
| Challenge: | Constructed languages (conlangs) have played diverse roles in art, philosophy, and international communication. foundation models have revolutionized creative generation in text, images, and beyond. |
| Approach: | They propose a multi-hop pipeline that decomposes language design into modular stages . they use LLMs' metalinguistic reasoning capabilities to encourage diversity . |
| Outcome: | The proposed pipeline decomposes language design into modular stages . it leverages LLMs’ metalinguistic reasoning capabilities to encourage diversity and self-refinement feedback to encourage consistency and typological diversity. |
Mitigating Open-Vocabulary Caption Hallucinations (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for image captioning ignore the long-tailed nature of hallucinations . a new framework is proposed to address hallucines in image captions in the open-vocabulary setting . |
| Approach: | They propose a framework to address hallucinations in image captioning in the open-vocabulary setting. |
| Outcome: | The proposed framework surpasses the CHAIR benchmark in diversity and accuracy in open-vocabulary captioning. |