Spandana Gella
Research Manager
AI Frontier Research
Spandana Gella is a Research Scientist and the Research Manager of the Multimodal Foundational Models Program. She holds a Ph.D. in Computer Science from University of Edinburgh, UK, where she was supervised by Prof. Mirella Lapata and Prof. Frank Keller. Prior to joining ServiceNow she worked at Amazon AI and Alexa AI for 6 years and interned at Meta AI Research and Microsoft Research. Her research focuses on building robust and safe multimodal foundation models. Her research has been published at various NLP/ML conferences and she is an active member of the academic community and organized workshops, shared tasks and served as area chair and has been a part of the program committees at NLP/ML conferences.
Intérêts
- Multimodal Models
- Safety
- Large Language Models
- Dialog
Publications
WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation.
Conference on Empirical Methods in Natural Language Processing (EMNLP),
2025.
BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning.
Conference on Language Modeling (COLM),
2025.
AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery.
Workshop at the Annual Meeting of the Association for Computational Linguistics (ACL),
2025.
SafeArena: Evaluating the Safety of Autonomous Web Agents.
International Conference on Machine Learning (ICML),
2025.
UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction.
International Conference on Machine Learning (ICML),
2025.
AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding.
Workshop at the International Conference of Learning Representation (ICLR),
2025.
WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation.
Workshop at the International Conference of Learning Representation (ICLR),
2025.
BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks.
International Conference of Learning Representations (ICLR),
2025.
BigDocs: A Permissively-Licensed Dataset for Training Vision-Language Models on Document and Code Tasks.
Workshop at the Neural Information Processing Systems (NeurIPS),
2024.