Profiles2022-2025
Jianhua Han
Huawei Noah's Ark Lab
8Papers
0Last author
15Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers8
- EMOVA: Empowering Language Models to See, Hear and Speak with Vivid EmotionsAuthor 15 of 31CVPR 2025
- Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake AnalysisAuthor 4 of 14ICLR 2024 · 47 citations
- NLIP: Noise-Robust Language-Image Pre-trainingAuthor 3 of 7AAAI 2023 · 44 citations
- Task-customized Masked Autoencoder via Mixture of Cluster-conditional ExpertsAuthor 3 of 7ICLR 2023 · 6 citations
- CapDet: Unifying Dense Captioning and Open-World Detection PretrainingAuthor 3 of 8CVPR 2023
- Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous DrivingAuthor 3 of 6CVPR 2023
- Effective Adaptation in Multi-Task Co-Training for Unified Autonomous DrivingAuthor 3 of 6NeurIPS 2022 · 53 citations
- Task-Customized Self-Supervised Pre-training with Scalable Dynamic RoutingAuthor 2 of 7AAAI 2022 · 30 citations
