Aishwarya Agrawal

Biography

Aishwarya Agrawal is an assistant professor in the Department of Computer Science and Operations Research at Université de Montréal, a Canada CIFAR AI Chair, and a core academic member of Mila – Quebec Artificial Intelligence Institute.

Agrawal also works as a research scientist one day a week at DeepMind. Previously, she held this position full time (August 2019 to December 2020). She completed her PhD in August 2019 at Georgia Tech, where she worked with Dhruv Batra and Devi Parikh.

Her research interests lie at the intersection of the following sub-disciplines of AI: computer vision, deep learning and natural language processing. The focus is developing AI systems that can ‘see’ (i.e., understand the contents of an image: who, what, where, doing what?) and ‘talk’ (i.e., communicate the understanding to humans in free-form natural language).

Aishwarya has received many awards and scholarships: Georgia Tech 2020 Sigma Xi Best PhD Thesis Award, 2020 Georgia Tech College of Computing Dissertation Award, 2019 Google Fellowship (declined due to graduation), 2019–2020 Facebook Fellowship (declined due to graduation) and 2018–2019 NVIDIA Graduate Fellowship. She was one of two runners-up in the 2019 AAAI/ACM SIGAI Dissertation Award, and was selected as a 2018 Rising Star in EECS.

She holds a bachelor's degree in electrical engineering with a minor in computer science and engineering from the Indian Institute of Technology Gandhinagar (2014).

Current Students

Saba Ahmadi

Collaborating researcher - Université de Montréal

Rabiul Awal

PhD - Université de Montréal

Collaborating researcher - University of British Columbia

Narges Erfan

Master's Research - McGill University

Principal supervisor :

James Clark

Kanishk Jain

PhD - Université de Montréal

Collaborating researcher - Korea University

Parisa Kordjamshidi

Independent visiting researcher - Michigan State University

Huy Le

Master's Research - Université de Montréal

PhD - Université de Montréal

Collaborating researcher - International Institute of Information Technology

Shravan Nayak

PhD - Université de Montréal

Luc Selmes

Professional Master's - Université de Montréal

Ankur Sikarwar

Master's Research - Université de Montréal

Heng Wei

Professional Master's - Université de Montréal

Qian Yang

PhD - Université de Montréal

Le Zhang

PhD - Université de Montréal

Publications

Discovering Failure Modes in Vision-Language Models using RL

Nishanth Anand

Vision-language Models (VLMs), despite achieving strong performance on multimodal benchmarks, often misinterpret straightforward visual conc… (see more)epts that humans identify effortlessly, such as counting, spatial reasoning, and viewpoint understanding. Previous studies manually identified these weaknesses and found that they often stem from deficits in specific skills. However, such manual efforts are costly, unscalable, and subject to human bias, which often overlooks subtle details in favor of salient objects, resulting in an incomplete understanding of a model's vulnerabilities. To address these limitations, we propose a Reinforcement Learning (RL)-based framework to automatically discover the failure modes or blind spots of any candidate VLM on a given data distribution without human intervention. Our framework trains a questioner agent that adaptively generates queries based on the candidate VLM's responses to elicit incorrect answers. Our approach increases question complexity by focusing on fine-grained visual details and distinct skill compositions as training progresses, consequently identifying 36 novel failure modes in which VLMs struggle. We demonstrate the broad applicability of our framework by showcasing its generalizability across various model combinations.

2026-04-05

arXiv (preprint)

Communicating about Space: Language-Mediated Spatial Integration Across Partial Views

Ankur Sikarwar

Debangan Mishra

Sudarshan Nikhil

Ponnurangam Kumaraguru

Humans build shared spatial understanding by communicating partial, viewpoint-dependent observations. We ask whether Multimodal Large Langua… (see more)ge Models (MLLMs) can do the same, aligning distinct egocentric views through dialogue to form a coherent, allocentric mental model of a shared environment. To study this systematically, we introduce COSMIC, a benchmark for Collaborative Spatial Communication. In this setting, two static MLLM agents observe a 3D indoor environment from different viewpoints and exchange natural-language messages to solve spatial queries. COSMIC contains 899 diverse scenes and 1250 question-answer pairs spanning five tasks. We find a capability hierarchy, MLLMs are most reliable at identifying shared anchor objects across views, perform worse on relational reasoning, and largely fail at building globally consistent maps, performing near chance, even for frontier models. Moreover, we find thinking capability yields gains in anchor grounding, but is insufficient for higher-level spatial communication. To contextualize model behavior, we collect 250 human-human dialogues. Humans achieve 95% aggregate accuracy, while the best model, Gemini-3-Pro-Thinking, reaches 72%, leaving substantial room for improvement. Moreover, human conversations grow more precise as partners align on a shared spatial understanding, whereas MLLMs keep exploring without converging, suggesting limited capacity to form and sustain a robust shared mental model throughout the dialogue. Our code and data is available at https://github.com/ankursikarwar/Cosmic.

2026-03-27

arXiv (preprint)

Observational Study of Maternal and Fetal Outcome in Posterior Reversible Encephalopathy Syndrome in Eclamptic Women in a Tertiary Care Institute

Prerna Kailashchand Gupta

Meenal Shailesh Sarmalkar

Madhuri A Mehendale

2026-02-02

Journal of South Asian Federation of Obstetrics and Gynaecology (published)

WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation

Christopher Pal

Juan A. Rodriguez

Sai Rajeswar

We present WebMMU, a multilingual benchmark that evaluates three core web tasks: (1) website visual question answering, (2) code editing inv… (see more)olving HTML/CSS/JavaScript, and (3) mockup-to-code generation. Unlike prior benchmarks that treat these tasks separately, WebMMU unifies them using expert-annotated, real-world web data to assess models'abilities in complex multi-step reasoning, precise element grounding, and functional UI comprehension and coding. Our evaluation shows that while multimodal large language models (MLLMs) perform well on basic information extraction, they struggle with reasoning and grounding, editing code to preserve functionality, and generating design-to-code that maintains hierarchy and supports multilingual content. These findings reveal key limitations in current MLLMs and underscore the need for improved multimodal and cross-lingual reasoning to build future web agents capable of automating diverse web development tasks.

2025-10-31

Conference on Empirical Methods in Natural Language Processing (published)

UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction

Shravan Nayak

Xiangru Jian

Kevin Qinghong Lin

Juan A. Rodriguez

Montek Kalsi

M. Tamer Özsu

Christopher Pal

Sai Rajeswar

Human Annotator

Autonomous agents that navigate Graphical User Interfaces (GUIs) to automate tasks like document editing and file management can greatly enh… (see more)ance computer workflows. While existing research focuses on online settings, desktop environments, critical for many professional and everyday tasks, remain underexplored due to data collection challenges and licensing issues. We introduce UI-Vision, the first comprehensive, license-permissive benchmark for offline, fine-grained evaluation of computer use agents in real-world desktop environments. Unlike online benchmarks, UI-Vision provides: (i) dense, high-quality annotations of human demonstrations, including bounding boxes, UI labels, and action trajectories (clicks, drags, and keyboard inputs) across 83 software applications, and (ii) three fine-to-coarse grained tasks—Element Grounding, Layout Grounding, and Action Prediction—with well-defined metrics to rigorously evaluate agents’ performance in desktop environments. Our evaluation reveals critical limitations in state-of-the-art models like UI-TARS-72B, including issues with understanding professional software, spatial reasoning, and complex actions like drag-and-drop. These findings highlight the challenges in developing fully autonomous computer-use agents. With UI-Vision, we aim to advance the development of more capable agents for real-world desktop tasks.

2025-10-05

Proceedings of the 42nd International Conference on Machine Learning (published)

proceedings.mlr.press

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

While image generation techniques are now capable of producing high-quality images that respect prompts which span multiple sentences, the t… (see more)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)

Learning What Matters: Prioritized Concept Learning via Relative Error-driven Sample Selection

Leonid Sigal

Instruction tuning has been central to the success of recent vision-language models (VLMs), but it remains expensive-requiring large-scale d… (see more)atasets, high-quality annotations, and large compute budgets. We propose PRioritized cOncept learninG via Relative Error-driven Sample Selection (PROGRESS), a data- and compute-efficient framework that enables VLMs to dynamically select what to learn next based on their evolving needs during training. At each stage, the model tracks its learning progress across skills and selects the most informative samples-those it has not already mastered and that are not too difficult to learn at the current stage of training. This strategy effectively controls skill acquisition and the order in which skills are learned. Specifically, we sample from skills showing the highest learning progress, prioritizing those with the most rapid improvement. Unlike prior methods, PROGRESS requires no upfront answer annotations, queries answers only on a need basis, avoids reliance on additional supervision from auxiliary VLMs, and does not require compute-heavy gradient computations for data selection. Experiments across multiple instruction-tuning datasets of varying scales demonstrate that PROGRESS consistently outperforms state-of-the-art baselines with much less data and supervision. Additionally, we show strong cross-architecture generalization and transferability to larger models, validating PROGRESS as a scalable solution for efficient learning.

2025-06-10

ES-FoMo @ International Conference on Machine Learning (published)

Assessing and Learning Alignment of Unimodal Vision and Language Models

Le Zhang

Qian Yang

How well are unimodal vision and language models aligned? Although prior work have approached answering this question, their assessment meth… (see more)ods do not directly translate to how these models are used in practical vision-language tasks. In this paper, we propose a direct assessment method, inspired by linear probing, to assess vision-language alignment. We identify that the degree of alignment of the SSL vision models depends on their SSL training objective, and we find that the clustering quality of SSL representations has a stronger impact on alignment performance than their linear separability. Next, we introduce Swift Alignment of Image and Language (SAIL), a efficient transfer learning framework that aligns pretrained unimodal vision and language models for downstream vision-language tasks. Since SAIL leverages the strengths of pretrained unimodal models, it requires significantly fewer (6%) paired image-text data for the multimodal alignment compared to models like CLIP which are trained from scratch. SAIL training only requires a single A100 GPU, 5 hours of training and can accommodate a batch size up to 32,768. SAIL achieves 73.4% zero-shot accuracy on ImageNet (vs. CLIP's 72.7%) and excels in zero-shot retrieval, complex reasoning, and semantic segmentation. Additionally, SAIL improves the language-compatibility of vision encoders that in turn enhance the performance of multimodal large language models. The entire codebase and model weights are open-source: https://lezhang7.github.io/sail.github.io/

2025-06-09

2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (published)

CulturalFrames: Assessing Cultural Expectation Alignment in Text-to-Image Models and Evaluation Metrics

Shravan Nayak

Mehar Bhatia

Xiaofeng Zhang

Verena Rieser

Lisa Anne Hendricks

Sjoerd van Steenkiste

Yash Goyal

Karolina Stanczak

The increasing ubiquity of text-to-image (T2I) models as tools for visual content generation raises concerns about their ability to accurate… (see more)ly represent diverse cultural contexts. In this work, we present the first study to systematically quantify the alignment of T2I models and evaluation metrics with respect to both explicit as well as implicit cultural expectations. To this end, we introduce CulturalFrames, a novel benchmark designed for rigorous human evaluation of cultural representation in visual generations. Spanning 10 countries and 5 socio-cultural domains, CulturalFrames comprises 983 prompts, 3637 corresponding images generated by 4 state-of-the-art T2I models, and over 10k detailed human annotations. We find that T2I models not only fail to meet the more challenging implicit expectations but also the less challenging explicit expectations. Across models and countries, cultural expectations are missed an average of 44% of the time. Among these failures, explicit expectations are missed at a surprisingly high average rate of 68%, while implicit expectation failures are also significant, averaging 49%. Furthermore, we demonstrate that existing T2I evaluation metrics correlate poorly with human judgments of cultural alignment, irrespective of their internal reasoning. Collectively, our findings expose critical gaps, providing actionable directions for developing more culturally informed T2I models and evaluation methodologies.

2025-06-09

ICML.cc/2025/Workshop/MoFA (poster)

REARANK: Reasoning Re-ranking Agent via Reinforcement Learning

Le Zhang

Bo Wang

Xipeng Qiu

Siva Reddy

We present REARANK, a large language model (LLM)-based listwise reasoning reranking agent. REARANK explicitly reasons before reranking, sign… (see more)ificantly improving both performance and interpretability. Leveraging reinforcement learning and data augmentation, REARANK achieves substantial improvements over baseline models across popular information retrieval benchmarks, notably requiring only 179 annotated samples. Built on top of Qwen2.5-7B, our REARANK-7B demonstrates performance comparable to GPT-4 on both in-domain and out-of-domain benchmarks and even surpasses GPT-4 on reasoning-intensive BRIGHT benchmarks. These results underscore the effectiveness of our approach and highlight how reinforcement learning can enhance LLM reasoning capabilities in reranking.

2024-12-31

EMNLP (published)

Improving Text-to-Image Consistency via Automatic Prompt Optimization

Oscar Mañas

Pietro Astolfi

Melissa Hall

Candace Ross

Jack Urbanek

Adina Williams

Adriana Romero-Soriano

Michal Drozdzal

Impressive advances in text-to-image (T2I) generative models have yielded a plethora of high performing models which are able to generate ae… (see more)sthetically appealing, photorealistic images. Despite the progress, these models still struggle to produce images that are consistent with the input prompt, oftentimes failing to capture object quantities, relations and attributes properly. Existing solutions to improve prompt-image consistency suffer from the following challenges: (1) they oftentimes require model fine-tuning, (2) they only focus on nearby prompt samples, and (3) they are affected by unfavorable trade-offs among image quality, representation diversity, and prompt-image consistency. In this paper, we address these challenges and introduce a T2I optimization-by-prompting framework, OPT2I, which leverages a large language model (LLM) to improve prompt-image consistency in T2I models. Our framework starts from a user prompt and iteratively generates revised prompts with the goal of maximizing a consistency score. Our extensive validation on two datasets, MSCOCO and PartiPrompts, shows that OPT2I can boost the initial consistency score by up to 24.9% in terms of DSG score while preserving the FID and increasing the recall between generated and real data. Our work paves the way toward building more reliable and robust T2I systems by harnessing the power of LLMs.

2024-12-02

TMLR (accepted)