Zhen Qin
- Papers
- 18
Cite
Notes
Only stored in your browser.
Authored papers
18FlashSampling: Fast and Memory-Efficient Exact Sampling
arXiv 2026
Tensor Product Attention Is All You Need
arXiv 2025
Hybrid Latent Reasoning via Reinforcement Learning
arXiv 2025
Accelerate TarFlow Sampling with GS-Jacobi Iteration
arXiv 2025
Group Representational Position Encoding
arXiv 2025
Higher-order Linear Attention
arXiv 2025
Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
arXiv 2024
Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention
arXiv 2024
Linear Attention Sequence Parallelism
arXiv 2024
Scaling Image Tokenizers with Grouped Spherical Quantization
arXiv 2024
TAVGBench: Benchmarking Text to Audible-Video Generation
arXiv 2024
Scaling Laws for Linear Complexity Language Models
arXiv 2024
CO2: Efficient Distributed Training with Full Communication-Computation Overlap
arXiv 2024
Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes
arXiv 2023
Fine-grained Audible Video Description
CVPR 2023 1
Accelerating Toeplitz Neural Network with Constant-time Inference Complexity
arXiv 2023
cosFormer: Rethinking Softmax in Attention
cosformer-rethinking-softmax-in-attention
The Devil in Linear Transformer
arXiv 2022
Affiliations
Frequent co-authors
10from 18 papers