Songlin Yang
- Kimi Linear: An Expressive, Efficient Attention Architecture
2025/10/30 by Kimi Team, Yu Zhang, Zhang, Yu +116 · 10 voices · 23 citations
#cs.CL #cs.LG
- Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
2025/05/10 by Zihan Qiu, Qiu, Zihan, Zekun Wang +23 · 3 voices · 39 citations
Computer Science · #Topic Modeling #Machine Learning in Healthcare #Big Data and Digital Economy
- Log-Linear Attention
2025/06/05 by Han Guo, Songlin Yang, Guo, Han +11 · 2 voices · 12 citations
Computer Science · #Machine Learning in Healthcare #Parallel Computing and Optimization Techniques #Topic Modeling #cs.LG
- Parallelizing Linear Transformers with the Delta Rule over Sequence Length
2024/06/10 by Songlin Yang, Bailin Wang, Yang, Songlin +7 · 61 citations
Computer Science · #Cellular Automata and Applications #Computability, Logic, AI Algorithms #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Quantum Computing Algorithms and Architecture
- Gated Delta Networks: Improving Mamba2 with Delta Rule
2024/12/09 by Songlin Yang, Yang, Songlin, Jan Kautz +3 · 70 citations
Computer Science · #Embedded Systems Design Techniques
- HGRN2: Gated Linear RNNs with State Expansion
2024/04/11 by Zhen Qin, Songlin Yang, Qin, Zhen +11 · 17 citations
Computer Science · #Advanced Neural Network Applications #Computation and Language (cs.CL) #FOS: Computer and information sciences #Speech Recognition and Synthesis #Topic Modeling
- Hierarchically Gated Recurrent Neural Network for Sequence Modeling
2023/11/08 by Zhen Qin, Songlin Yang, Qin, Zhen +3 · 13 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning in Bioinformatics #Natural Language Processing Techniques #Topic Modeling
- Test-Time Training Done Right
2025/05/29 by Tianyuan Zhang, Sai Bi, Zhang, Tianyuan +15 · 29 citations
Psychology · #Human Resource Development and Performance Evaluation
- Gated Slot Attention for Efficient Linear-Time Sequence Modeling
2024/09/11 by Yu Zhang, Songlin Yang, Zhang, Yu +21 · 11 citations
Computer Science · #Computation and Language (cs.CL) #Embedded Systems Design Techniques #FOS: Computer and information sciences #Parallel Computing and Optimization Techniques
- PaTH Attention: Position Encoding via Accumulating Householder Transformations
2025/05/22 by Songlin Yang, Yang, Songlin, Yikang Shen +12 · 12 citations
Computer Science · #Topic Modeling #Natural Language Processing Techniques #Multimodal Machine Learning Applications
- MesaNet: Sequence Modeling by Locally Optimal Test-Time Training
2025/06/05 by Johannes von Oswald, Nino Scherrer, von Oswald, Johannes +30 · 11 citations
Computer Science · #Topic Modeling #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning
- Context-Aware Talking-Head Video Editing
2023/08/01 by Songlin Yang, Yang, Songlin, Wei Wang +9 · 2 citations
Computer Science · #FOS: Computer and information sciences #Face recognition and analysis #Multimedia (cs.MM) #Speech and Audio Processing #Video Analysis and Summarization
- Joint Entity and Relation Extraction with Span Pruning and Hypergraph Neural Networks
2023/10/26 by Zhaohui Yan, Yan, Zhaohui, Songlin Yang +5 · 2 citations
Computer Science · Decision Sciences · #Topic Modeling #Advanced Graph Neural Networks #Data Quality and Management
- Second-Order Unsupervised Neural Dependency Parsing
2020/10/28 by Songlin Yang, Yong Jiang, Yang, Songlin +5 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling
- Learning Dense Correspondence for NeRF-Based Face Reenactment
2023/12/16 by Songlin Yang, Wei Wang, Yang, Songlin +11 · 2 citations
Computer Science · #Advanced Image Processing Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Face recognition and analysis #Generative Adversarial Networks and Image Synthesis
- Neural Bi-Lexicalized PCFG Induction
2021/05/31 by Songlin Yang, Yang, Songlin, Yanpeng Zhao +3 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech Recognition and Synthesis #Topic Modeling
- Combining (second-order) graph-based and headed-span-based projective dependency parsing
2021/08/12 by Songlin Yang, Yang, Songlin, Kewei Tu +1 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning in Bioinformatics #Natural Language Processing Techniques #Topic Modeling
- Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs
2022/05/01 by Songlin Yang, Yang, Songlin, Wei Liu +3 · 1 citation
Computer Science · #Topic Modeling #Natural Language Processing Techniques #Multimodal Machine Learning Applications
- A Controlled Study on Long Context Extension and Generalization in LLMs
2024/09/18 by Yi Lü, Lu, Yi, Jing Nathan Yan +15 · 2 citations
Computer Science · #Computation and Language (cs.CL) #Data Mining Algorithms and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Semantic Web and Ontologies
- Simple Hardware-Efficient PCFGs with Independent Left and Right Productions
2023/10/23 by Wei Liu, Songlin Yang, Liu, Wei +5 · 1 citation
Computer Science · #Algorithms and Data Compression #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Topic Modeling
- Is It Possible to Backdoor Face Forgery Detection with Natural Triggers?
2023/12/31 by Xiaoxuan Han, Han, Xiaoxuan, Songlin Yang +7 · 1 citation
Computer Science · #Adversarial Robustness in Machine Learning #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Face recognition and analysis #Generative Adversarial Networks and Image Synthesis
- Dense Semantic Matching with VGGT Prior
2025/09/25 by Songlin Yang, Yang, Songlin, Wei, Tianyi +8 · 1 citation
Computer Science · #Topic Modeling #Natural Language Processing Techniques