Get started
Author

Kai Han

Observed name: Han, Kai
ORCID: 0000-0002-7995-9999
Observed ORCID: 0000-0002-7995-9999
OpenAlex ID: A5101828117
DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models
2024 · He, Wei, Han, Kai, et al. · arXiv (Cornell University) · 50
PDF
FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition
2024 · Huang, Xiaohu, Zhou, Hao, et al. · arXiv (Cornell University) · 25
PDF
Data-efficient Large Vision Models through Sequential Autoregression
2024 · Guo, Jianyuan, Hao, Zhiwei, et al. · arXiv (Cornell University) · 18
PDF
SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning
2024 · Wang, Hongjun, Vaze, Sagar, et al. · arXiv (Cornell University) · 17
PDF
Eve: Efficient Multimodal Vision Language Models with Elastic Visual Experts
2025 · Miao Rang, Zhenni Bi, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 13
PDF
DenseSSM: State Space Models with Dense Hidden Connection for Efficient Large Language Models
2025 · Wei He, Kai Han, et al. · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 12
PDF
Guide3D: Create 3D Avatars from Text and Image Guidance
2023 · Cao, Yukang, Cao, Yan-Pei, et al. · arXiv (Cornell University) · 11
PDF
Diffusion In Diffusion: Reclaiming Global Coherence in Semi-Autoregressive Diffusion
2026 · Ma, Linrui, Cui, Yufei, et al. · arXiv (Cornell University) · 9
PDF
Multimodal Latent Reasoning via Hierarchical Visual Cues Injection
2026 · Zhang, Yiming, Yan, Qiangyu, et al. · arXiv (Cornell University) · 7
PDF
Agentic Routing: The Harness-Native Data Flywheel
2026 · Liu, Xinchen, Zhou, Hang, et al. · arXiv (Cornell University) · 5
PDF
LightCLIP: Learning Multi-Level Interaction for Lightweight Vision-Language Models
2023 · Nie, Ying, He, Wei, et al. · arXiv (Cornell University) · 5
PDF
Top 10 Open Challenges Steering the Future of Diffusion Language Model and Its Variants
2026 · Wang, Yunhe, Han, Kai, et al. · arXiv (Cornell University) · 4
PDF
Category Feature Transformer for Semantic Segmentation
2023 · Tang, Quan, Liu, Chuanjian, et al. · arXiv (Cornell University) · 4
PDF
Mask Is What DLLM Needs: A Masked Data Training Paradigm for Diffusion LLMs
2026 · Ma, Linrui, Cui, Yufei, et al. · arXiv (Cornell University) · 3
PDF
Beyond Masks: Efficient, Flexible Diffusion Language Models via Deletion-Insertion Processes
2026 · Ding, Fangyu, Ding, Ding, et al. · arXiv (Cornell University) · 3
PDF
What Makes a Good Visual Representation for Spatial Understanding in MLLMs?
2026 · Huang, Xiaohu, Guo, Yumin, et al. · arXiv (Cornell University) · 1
PDF
VAGS: Velocity Adaptive Guidance Scale for Image Editing and Generation
2026 · Luo, Yan, Aidara, Ahmadou, et al. · arXiv (Cornell University) · 1
PDF
Where Natural Language Ends in Agents: Executable Skill Composition with MetaSkill
2026 · Shu, Meng, He, Wei, et al. · arXiv (Cornell University)
PDF
Beyond Single Expert: Harmonizing Diverse Visual Priors in MLLMs for Spatial Understanding
2026 · Lin, Xiao, Huang, Xiaohu, et al. · arXiv (Cornell University)
PDF
Scene-Level Heterogeneous Physics Simulation with 3D Gaussian Splats
2026 · Liu, Xiaoyang, Wu, Shangzhe, et al. · arXiv (Cornell University)
PDF
Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders
2026 · Jiang, Yitong, Wang, Hongjun, et al. · arXiv (Cornell University)
PDF
iVGR: Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement Learning
2026 · Zhang, Chang-Bin, Zhong, Yujie, et al. · arXiv (Cornell University)
PDF
CodeBind: Decoupled Representation Learning for Multimodal Alignment with Unified Compositional Codebook
2026 · Chen, Zeyu, Li, Jie, et al. · arXiv (Cornell University)
PDF
Generalized Category Discovery under Domain Shifts: From Vision to Vision-Language Models
2026 · Wang, Hongjun, Hu, Po, et al. · arXiv (Cornell University)
PDF
MHPO: Modulated Hazard-aware Policy Optimization for Stable Reinforcement Learning
2026 · Wang, Hongjun, Liu, Wei, et al. · arXiv (Cornell University)
PDF
Works count: 27
Citation count: 194
H-index: 8
I10-index: 7
Year
Topic
Type