Senior Research Scientist
Adobe Research
Seattle, WA
My name is Jiuxiang Gu (顾久祥). I am a Senior Research Scientist at Adobe Research in Seattle. I received my Ph.D. from Nanyang Technological University, Singapore (2016.1–2019.5), under the supervision of Prof. Jianfei Cai, Dr. Gang Wang, and Prof. Tsuhan Chen. I currently serve as an Area Chair for ICLR 2025 and WACV 2024/2025, a Senior Program Committee Member for IJCAI 2021–2024, and a Program Committee Member for AAAI 2021–2023, NAACL 2021, and others. My research journey began in hardware design. From 2010 to 2015, I worked as an ASIC design engineer. In 2015, I made the transition to Artificial Intelligence. My current research interests include:
- Multimodal Foundation Models (LLM, MLLM, Diffusion LLM/MLLM, Text-to-Image/Video/3D Generation, Document Intelligence)
- Efficient Architecture & Scaling (Pruning, Quantization, KV Cache Optimization, Edge Deployment)
- Reasoning & Alignment (Chain-of-Thought, Hidden Thinking, Self-supervised Learning, Post-training)
- Impact & Production: Contribute to Adobe Firefly and Acrobat AI Assistant
Open to collaborations and internships in the above areas.
📧 Feel free to reach out: jigu@adobe.com / gu.jiuxiang@gmail.com
Selected Publications
2026
-
CVPR 2026Sparse-LaViDa: Sparse Multimodal Discrete Diffusion Language Models
-
ICLR 2026LaViDa-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation
2025
-
AAAI 2025Numerical pruning for efficient autoregressive models
2024
-
ICLR 2024 OralLrm: Large reconstruction model for single image to 3d
-
ICLR 2024ADoPD: A large-scale document page decomposition dataset
2021
-
NeurIPS 2021Unidoc: Unified pretraining framework for document understanding
2018
-
AAAI 2018 OralStack-Captioning: Coarse-to-Fine Learning for Image Captioning
-
CVPR 2018 SpotlightLook, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models
-
Pattern Recognition, 2018Recent advances in convolutional neural networks