Get started
Author

Han Shu

Observed name: Shu, Han
OpenAlex ID: A5150580108
TinySAM: Pushing the Envelope for Efficient Segment Anything Model
2025 · Han Shu, Wenshuo Li, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 51
PDF
Adder Attention for Vision Transformer
2021 · Han Shu, Jiahao Wang, et al. · neural information processing systems · 13
VEGA: Towards an End-to-End Configurable AutoML Pipeline
2020 · Wang, Bochao, Xu, Hang, et al. · arXiv (Cornell University) · 11
PDF
VLM-Pruner: Buffering for Spatial Sparsity in an Efficient VLM Centrifugal Token Pruning Paradigm
2025 · Wu, Zhenkai, Ma, Xiaowen, et al. · arXiv (Cornell University) · 1
PDF
MCPO: Modality-Contrastive Preference Optimization for Multimodal Chain-of-Thought Compression
2026 · Yang, Guangheng, Ni, Zhenliang, et al. · arXiv (Cornell University)
PDF
MM-IFEval-Pro: A Multilingual and Attack-Resistant Benchmark for Instruction-Following in Vision-Language Models
2026 · Xiao, Changming, Ni, Zhenliang, et al. · arXiv (Cornell University)
PDF
CapProbe: Evaluating Detailed Image Captions via Full-Scene Dense Question Answering
2026 · Huang, Mouxiao, Yan, Qiangyu, et al. · arXiv (Cornell University)
PDF
SlimVLM: Sensitivity-aware Dynamic Structured Pruning with Adaptive Visual Token Selection for Efficient Vision-Language Models
2026 · Wen, Yaozhi, Guo, Jialong, et al. · arXiv (Cornell University)
PDF
Thinking-while-speaking: A Controlled, Interleaved Reasoning Method for Real-Time Speech Generation
2026 · Du, Xuan, Yan, Qiangyu, et al. · arXiv (Cornell University)
PDF
TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model
2026 · Ding, Zhaoyuan, Yang, Yijing, et al. · arXiv (Cornell University)
PDF
SJD-PAC: Accelerating Speculative Jacobi Decoding via Proactive Drafting and Adaptive Continuation
2026 · Kang, Jialiang, Shu, Han, et al. · arXiv (Cornell University)
PDF
Works count: 13
Citation count: 77
H-index: 3
I10-index: 3
Year
Topic
Type