Get started
Author

Zhiyuan Liu

Observed name: Liu, Zhiyuan
Institution: Tsinghua University
OpenAlex ID: A5124454553
RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework
2024 · Zhu, Kunlun, Luo, Yifan, et al. · arXiv (Cornell University) · 2
PDF
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
2026 · Cui, Junbo, Xu, Bokai, et al. · arXiv (Cornell University) · 1
PDF
MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling
2026 · MiniCPM Team, An, Wenhao, et al. · arXiv (Cornell University) · 1
PDF
UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models
2026 · Association for Computational Linguistics 2026, Cui, Junbo, et al. · Underline Science Inc.
StateX: Enhancing RNN Recall via Post-training State Expansion
2026 · Association for Computational Linguistics 2026, Chen, Yingfa, et al. · Underline Science Inc.
Test-Time Deep Thinking to Explore Implicit Rules
2026 · Chen, Wentong, Cong, Xin, et al. · arXiv (Cornell University)
PDF
Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation
2026 · Zhang, Yichen, Peng, Da, et al. · arXiv (Cornell University)
PDF
APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention
2026 · Huang, Yuxiang, Li, Mingye, et al. · arXiv (Cornell University)
PDF
Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts
2026 · Yingfa Chen, Zhen Leng Thai, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
A Partial-Attention and Multi-Scale Fusion Framework for Efficient Object Detection in Unmanned Aerial Vehicle Imagery
2026 · kang tan, Hu Yao, et al. · SSRN Electronic Journal
Rethinking the Role of Efficient Attention in Hybrid Architectures
2026 · Ziqing Qiao, Yinuo Xu, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices
2024 · Huang, Yuxiang, Yuan, Binhang, et al. · arXiv (Cornell University)
PDF
Works count: 17
Citation count: 4
H-index: 1
I10-index:
Year
Topic
Type