52 citations · 52 across the 4 of their papers we have counts for
6 papers
EAGER: Enhancing Generative Event Extraction via Reinforcement Learning with Verifiable Rewards
Omar Adjali, Siting Liang, Omair Shahzad Bhatti +1
End-to-end event extraction remains challenging for large language models as it requires simultaneous identification of event triggers, classification of event types, and extractio…
Evaluating Explanation-Driven Vision-Language Reasoning via Generation Order Interventions
Siting Liang, Luca Rippe, Omar Adjali +1
Natural language explanation generation serves as a key mechanism for exposing and evaluating vision-language reasoning. Prior work on explanation-driven vision-language models pre…
A Scalable Cross-Domain Event Extraction System via a Unified Generative Training Framework
Siting Liang, Omar Adjali, Omair Shahzad Bhatti +1
Event extraction is fundamental to information extraction. Prior approaches often separate event detection and argument extraction or depend on dataset-specific designs, limiting s…
A Multi-Domain and Multi-Task Generative Framework with Explicit Task and Domain Conditioning for Cross-Domain Event Extraction
Siting Liang, Omar Adjali, Daniel Sonntag
Event extraction aims to identify event triggers, classify event types, and extract arguments to construct structured event representations. Despite strong in-domain performance, d…
WOLF-VLA: Whole-Body Humanoid Optimal Locomotion Framework for Vision-Language-Action Learning
Melya Boukheddimi, Omar Adjali, Daniel Sontag +1
Vision-Language-Action (VLA) models have recently demonstrated strong generalization in robotic manipulation, yet their applicability to whole-body, contact-rich humanoid locomotio…
Multimodal Entity Linking for Tweets
Omar Adjali, Romaric Besançon, Olivier Ferret +2
In many information extraction applications, entity linking (EL) has emerged as a crucial task that allows leveraging information about named entities from a knowledge base. In thi…