Portrait de Saba Ahmadi n'est pas disponible

Saba Ahmadi

Collaborateur·rice de recherche - UdeM
Superviseur⋅e principal⋅e
Aishwarya Agrawal
Sujets de recherche
Apprentissage multimodal
Modèles génératifs
Vision par ordinateur
Site web
Google Scholar
GitHub

Publications

The Promise of RL for Autoregressive Image Editing
Saba Ahmadi
Rabiul Awal
Ankur Sikarwar
Amirhossein Kazemnejad
Ge Ya Luo
Juan A. Rodriguez
Sai Rajeswar
Siva Reddy
Christopher Pal
Benno Krojer
Aishwarya Agrawal
While image generation techniques are now capable of producing high-quality images that respect prompts which span multiple sentences, the t… (voir plus)ask of text-guided image editing remains a challenge. Even edit requests that consist of only a few words often fail to be executed correctly. We explore three strategies to enhance performance on a wide range of image editing tasks: supervised fine-tuning (SFT), reinforcement learning (RL), and Chain-of-Thought (CoT) reasoning. In order to study all these components in one consistent framework, we adopt an autoregressive multimodal model that processes textual and visual tokens in a unified manner. We find RL combined with a large multi-modal LLM verifier to be the most effective of these strategies. As a result, we release EARL: Editing with Autoregression and RL, a strong RL-based image editing model that performs competitively on a diverse range of edits compared to strong baselines, despite using much less training data. Thus, EARL pushes the frontier of autoregressive multimodal models on image editing. We release our code, training data, and trained models at https://github.com/mair-lab/EARL.
2025-09-17
NeurIPS.cc/2025/Conference (poster)
doi.org
openreview.net
VisMin: Visual Minimal-Change Understanding
Rabiul Awal
Saba Ahmadi
Le Zhang
Aishwarya Agrawal
Fine-grained understanding of objects, attributes, and relationships between objects is crucial for visual-language models (VLMs). Existing … (voir plus)benchmarks primarily focus on evaluating VLMs' capability to distinguish between two very similar captions given an image. In this paper, we introduce a new, challenging benchmark termed Visual Minimal-Change Understanding (VisMin), which requires models to predict the correct image-caption match given two images and two captions. The image pair and caption pair contain minimal changes, i.e., only one aspect changes at a time from among the following: object, attribute, count, and spatial relation. These changes test the models' understanding of objects, attributes (such as color, material, shape), counts, and spatial relationships between objects. We built an automatic framework using large language models and diffusion models, followed by a rigorous 4-step verification process by human annotators. Empirical experiments reveal that current VLMs exhibit notable deficiencies in understanding spatial relationships and counting abilities. We also generate a large-scale training dataset to finetune CLIP and Idefics2, showing significant improvements in fine-grained understanding across benchmarks and in CLIP's general image-text alignment. We release all resources, including the benchmark, training data, and finetuned model checkpoints, at https://vismin.net/.
2024-09-24
NeurIPS.cc/2024/Conference (poster)
doi.org
openreview.net
An Examination of the Robustness of Reference-Free Image Captioning Evaluation Metrics
Saba Ahmadi
Aishwarya Agrawal
2023-12-31
EACL (Findings) (publié)
doi.org
arxiv.org
MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting
Oscar Mañas
Pau Rodríguez
Saba Ahmadi
Aida Nematzadeh
Yash Goyal
Aishwarya Agrawal
Large pre-trained models have proved to be remarkable zero- and (prompt-based) few-shot learners in unimodal vision and language tasks. We p… (voir plus)ropose MAPL, a simple and parameter-efficient method that reuses frozen pre-trained unimodal models and leverages their strong generalization capabilities in multimodal vision-language (VL) settings. MAPL learns a lightweight mapping between the representation spaces of unimodal models using aligned image-text data, and can generalize to unseen VL tasks from just a few in-context examples. The small number of trainable parameters makes MAPL effective at low-data and in-domain learning. Moreover, MAPL's modularity enables easy extension to other pre-trained models. Extensive experiments on several visual question answering and image captioning benchmarks show that MAPL achieves superior or competitive performance compared to similar methods while training orders of magnitude fewer parameters. MAPL can be trained in just a few hours using modest computational resources and public datasets. We release our code and pre-trained model weights at https://github.com/mair-lab/mapl.
2023-04-30
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics (publié)
doi.org
arxiv.org