Zhang, Jiaqi
YOU?
Author Swipe
View article: Causal Structure and Representation Learning with Biomedical Applications
Causal Structure and Representation Learning with Biomedical Applications Open
Massive data collection holds the promise of a better understanding of complex phenomena and, ultimately, better decisions. Representation learning has become a key driver of deep learning applications, as it allows learning latent spaces …
View article: Causal Structure and Representation Learning with Biomedical Applications
Causal Structure and Representation Learning with Biomedical Applications Open
Massive data collection holds the promise of a better understanding of complex phenomena and, ultimately, better decisions. Representation learning has become a key driver of deep learning applications, as it allows learning latent spaces …
View article: Causal Structure and Representation Learning with Biomedical Applications
Causal Structure and Representation Learning with Biomedical Applications Open
Massive data collection holds the promise of a better understanding of complex phenomena and, ultimately, better decisions. Representation learning has become a key driver of deep learning applications, as it allows learning latent spaces …
View article: Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies
Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies Open
In this work, we conduct a systematic analysis of Native Sparse Attention (NSA) and propose targeted improvements that enhance long-context modeling. A key insight is that alternating between local (sliding-window) and global (compression,…
View article: Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies
Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies Open
In this work, we conduct a systematic analysis of Native Sparse Attention (NSA) and propose targeted improvements that enhance long-context modeling. A key insight is that alternating between local (sliding-window) and global (compression,…
View article: Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies
Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies Open
In this work, we conduct a systematic analysis of Native Sparse Attention (NSA) and propose targeted improvements that enhance long-context modeling. A key insight is that alternating between local (sliding-window) and global (compression,…
View article: Introducing LongCat-Flash-Thinking: A Technical Report
Introducing LongCat-Flash-Thinking: A Technical Report Open
We present LongCat-Flash-Thinking, an efficient 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model. Its advanced capabilities are cultivated through a meticulously crafted training process, beginning with long Chain…
View article: LongCat-Flash Technical Report
LongCat-Flash Technical Report Open
We introduce LongCat-Flash, a 560-billion-parameter Mixture-of-Experts (MoE) language model designed for both computational efficiency and advanced agentic capabilities. Stemming from the need for scalable efficiency, LongCat-Flash adopts …
View article: Discrete Superconvergence Analysis for Quantum Magnus Algorithms of Unbounded Hamiltonian Simulation
Discrete Superconvergence Analysis for Quantum Magnus Algorithms of Unbounded Hamiltonian Simulation Open
Motivated by various applications, unbounded Hamiltonian simulation has recently garnered great attention. Quantum Magnus algorithms, designed to achieve commutator scaling for time-dependent Hamiltonian simulation, have been found to be p…
View article: Additional file 1 of LncRNA MEG8 promotes deep vein thrombosis by sponging miR-296-5p to regulate human umbilical vein endothelial cells
Additional file 1 of LncRNA MEG8 promotes deep vein thrombosis by sponging miR-296-5p to regulate human umbilical vein endothelial cells Open
Supplementary Material 1.
View article: Additional file 1 of LncRNA MEG8 promotes deep vein thrombosis by sponging miR-296-5p to regulate human umbilical vein endothelial cells
Additional file 1 of LncRNA MEG8 promotes deep vein thrombosis by sponging miR-296-5p to regulate human umbilical vein endothelial cells Open
Supplementary Material 1.
View article: LncRNA MEG8 promotes deep vein thrombosis by sponging miR-296-5p to regulate human umbilical vein endothelial cells
LncRNA MEG8 promotes deep vein thrombosis by sponging miR-296-5p to regulate human umbilical vein endothelial cells Open
Aim This study explored the diagnostic value and molecular mechanism of lncRNA MEG8 in deep vein thrombosis (DVT). Methods This study included 120 patients with DVT and 100 healthy individuals as research subjects. Expression of lncRNA MEG…
View article: LncRNA MEG8 promotes deep vein thrombosis by sponging miR-296-5p to regulate human umbilical vein endothelial cells
LncRNA MEG8 promotes deep vein thrombosis by sponging miR-296-5p to regulate human umbilical vein endothelial cells Open
Aim This study explored the diagnostic value and molecular mechanism of lncRNA MEG8 in deep vein thrombosis (DVT). Methods This study included 120 patients with DVT and 100 healthy individuals as research subjects. Expression of lncRNA MEG…