Jiaya Jia

Hong Kong University of Science and Technology — Hong Kong

Computer Science · Physical Sciences

105h-index74.4kcitations434works9.72yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Vision and Imaging(128), Advanced Neural Network Applications(109), Advanced Image Processing Techniques(97), Advanced Image and Video Retrieval Techniques(90), Domain Adaptation and Few-Shot Learning(66)

Publications434 total

Mini-Gemini: Mining the Potential of Multi-Modality Vision Language Models
IEEE Transactions on Pattern Analysis and Machine Intelligence·2025· 13 cited
SmartSwitch: Advancing LLM Reasoning by Overcoming Underthinking via Promoting Deeper Thought Exploration
arXiv (Cornell University)·2025Open Access
InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
arXiv (Cornell University)·2025Open Access
DreamOmni2: Multimodal Instruction-based Editing and Generation
arXiv (Cornell University)·2025Open Access
Stratified GRPO: Handling Structural Heterogeneity in Reinforcement Learning of LLM Search Agents
arXiv (Cornell University)·2025Open Access
From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models
arXiv (Cornell University)·2025Open Access
MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech
arXiv (Cornell University)·2025Open Access
VLPose: Bridging the Domain Gap in Pose Estimation With Language-Vision Tuning
IEEE Transactions on Pattern Analysis and Machine Intelligence·2025
DreamVE: Unified Instruction-based Image and Video Editing
arXiv (Cornell University)·2025Open Access
VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
arXiv (Cornell University)·2025Open Access
Generative Video Propagation
2025· 2 cited
VisionZip: Longer is Better but Not Necessary in Vision Language Models
2025· 5 cited
DreamOmni: Unified Image Generation and Editing
2025
Logits-Based Finetuning
arXiv (Cornell University)·2025Open Access
RTime-QA: A Benchmark for Atomic Temporal Event Understanding in Large Multi-modal Models
arXiv (Cornell University)·2025Open Access
VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning
arXiv (Cornell University)·2025Open Access
TraveLLaMA: A Multimodal Travel Assistant with Large-Scale Dataset and Structured Reasoning
arXiv (Cornell University)·2025Open Access
Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?
arXiv (Cornell University)·2025Open Access
GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning
arXiv (Cornell University)·2025Open Access
MagicMirror: ID-Preserved Video Generation in Video Diffusion Transformers
arXiv (Cornell University)·2025· 1 citedOpen Access
page 1 of 22Next →

Frequent Co-authors

Hengshuang Zhao(12), Jianping Shi(11), Shu Liu(9), Xiaoyong Shen(9), Xiaojuan Qi(7), Li Xu(5), Li Jiang(4), Xin Tao(4), Chi‐Wing Fu(4), Xu Li(4), Renjie Liao(4), Lu Qi(3), Qiong Yan(3), Hongyun Gao(3), Cewu Lu(3), Chi–Keung Tang(3), Raquel Urtasun(3), Xiaogang Wang(2), Haifang Qin(2), Vladlen Koltun(2)