Lune

Profiles2021-2026

Jiahua Dong

Zayed University of Artificial Intelligence

18Papers
1Last author
47Unique co-authors
7First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers18

  1. PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action ModelAuthor 4 of 8ICLR 2026 · 20 citations
  2. SeqWalker: Sequential-Horizon Vision-and-Language Navigation with Hierarchical PlanningAuthor 6 of 8AAAI 2026 · 2 citations
  3. Bring Your Dreams to Life: Continual Text-to-Video CustomizationAuthor 1 of 11AAAI 2026 · 1 citation
  4. Lifelong Language-Conditioned Robotic Manipulation LearningAuthor 5 of 8AAAI 2026
  5. STUR3D: Spatio-Temporal Unified Representation Learning for 3D Object DetectionAuthor 5 of 6CVPR 2026
  6. Towards Efficient and Effective Interactive 3D SegmentationAuthor 3 of 4AAAI 2026
  7. Enhancing Multimodal Continual Instruction Tuning with BranchLoRAAuthor 5 of 8ACL 2025 · 9 citations
  8. Hierarchical Visual Prompt Learning for Continual Video Instance SegmentationAuthor 1 of 8ICCV 2025
  9. MM-LLMs: Recent Advances in MultiModal Large Language ModelsAuthor 3 of 7ACL Findings 2024 · 260 citations
  10. How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization?Author 1 of 9NeurIPS 2024 · 42 citations
  11. Heterogeneous Forgetting Compensation for Class-Incremental LearningAuthor 1 of 4ICCV 2023 · 28 citations
  12. Continual Named Entity Recognition without Catastrophic ForgettingAuthor 3 of 7EMNLP 2023 · 16 citations
  13. Federated Incremental Semantic SegmentationAuthor 1 of 6CVPR 2023
  14. Is Out-of-Distribution Detection Learnable?Author 4 of 6NeurIPS 2022 · 188 citations
  15. Confident Anchor-Induced Multi-Source Free Domain AdaptationAuthor 1 of 5NeurIPS 2021 · 107 citations
  16. I3DOL: Incremental 3D Object Learning without Catastrophic ForgettingAuthor 1 of 5AAAI 2021 · 38 citations
  17. Generative Partial Visual-Tactile Fused Object ClusteringAuthor 4 of 6AAAI 2021 · 16 citations
  18. Unsupervised Dense Deformation Embedding Network for Template-Free Shape CorrespondenceAuthor 3 of 3ICCV 2021 · 4 citations
Dusk over the sea between two cliffs drawn in fine vertical lines