2025: Preprint 'A Simple and Effective Reinforcement Learning Method for Text-to-Image Diffusion Fine-tuning' on arXiv.
2025: Paper 'Multi-Modal Large Language Models as Effective Vision Learners' accepted at WACV 2025.
2023: Survey paper on Co-Speech Gestures accepted in STAR track at Eurographics 2023.
2022: Paper on Low-Resource Adaptation of Spatio-Temporal Crossmodal Generative Models accepted at CVPR 2022; Highlighted Reviewer at ICLR 2022.
2020: Multiple papers accepted at EMNLP Findings, IVA, and ECCV on co-speech gesture generation, personality effects, and style transfer.
2020: Released PATS (Pose-Audio-Transcripts-Style) Dataset and code for style transfer in co-speech gesture animation.
2019: Papers accepted at ICMI 2019 and 3DV 2019 on personalized avatar pose forecasting in dyadic conversations.
2018: Paper 'Lattice Recurrent Units' accepted at AAAI 2018.
2017: Co-authored a survey on Multimodal Machine Learning; contributed a book chapter 'Challenges and applications in multimodal machine learning' in The Handbook of Multimodal-Multisensor Interfaces (2018).