Selected Publications

MotionEdit: Benchmarking and Learning Motion-Centric Image Editing

Published in arXiv, 2025

We introduce MotionEdit, a novel dataset and benchmark for motion-centric image editing. We also propose MotionNFT (Motion-guided Negative-aware FineTuning), a post-training framework with motion alignment rewards to guide models on motion editing task.

Download Paper

CompAlign: Improving Compositional Text-to-Image Generation with a Complex Benchmark and Fine-Grained Feedback

Published in Arxiv, 2025

Download Paper

Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generation

Published in ICLR SeT LLM, 2023

Download Paper

*[Best Paper, NAACL TrustNLP 2024] White Men Lead, Black Women Help? Benchmarking and Mitigating Language Agency Social Biases in LLMs

Published in ACL, 2025

Download Paper

The Male CEO and the Female Assistant: Evaluation and Mitigation of Gender Biases in Text-To-Image Generation of Dual Subjects

Published in ACL, 2025

Download Paper

The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention

Published in EMNLP, 2024

Download Paper

Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation

Published in Arxiv, 2024

Download Paper

Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems

Published in EMNLP, 2023

Download Paper

‘Kelly is a Warm Person, Joseph is a Role Model’: Gender Biases in LLM-Generated Reference Letters

Published in EMNLP, 2023

Download Paper

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning

Published in EMNLP, 2025

Download Paper

LUME: LLM Unlearning with Multitask Evaluations

Published in EMNLP, 2025

Download Paper