25 citations · 58 across the 25 of their papers we have counts for
25 papers
Elucidating the Design Space of Decay in Linear Attention
Zhen Qin, Xuyang Shen, Yiran Zhong
This paper presents a comprehensive investigation into the decay mechanisms inherent in linear complexity sequence models. We systematically delineate the design space of decay mec…
Learning Spatial Decay for Vision Transformers
Yuxin Mao, Zhen Qin, Jinxing Zhou +4
Vision Transformers (ViTs) have revolutionized computer vision, yet their self-attention mechanism lacks explicit spatial inductive biases, leading to suboptimal performance on spa…
Autoregressive Image Generation with Linear Complexity: A Spatial-Aware Decay Perspective
Yuxin Mao, Zhen Qin, Jinxing Zhou +6
Autoregressive (AR) models have garnered significant attention in image generation for their ability to effectively capture both local and global structures within visual data. How…
Deep Non-rigid Structure-from-Motion Revisited: Canonicalization and Sequence Modeling
Hui Deng, Jiawei Shi, Zhen Qin +2
Non-Rigid Structure-from-Motion (NRSfM) is a classic 3D vision problem, where a 2D sequence is taken as input to estimate the corresponding 3D sequence. Recently, the deep neural n…
Scaling Laws for Linear Complexity Language Models
Xuyang Shen, Dong Li, Ruitao Leng +3
The interest in linear complexity models for large language models is on the rise, although their scaling capacity remains uncertain. In this study, we present the scaling laws for…
Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention
Zhen Qin, Weigao Sun, Dong Li +3
We present Lightning Attention, the first linear attention implementation that maintains a constant training speed for various sequence lengths under fixed memory consumption. Due…
You Only Scan Once: Efficient Multi-dimension Sequential Modeling with LightNet
Zhen Qin, Yuxin Mao, Xuyang Shen +4
Linear attention mechanisms have gained prominence in causal language models due to their linear computational complexity and enhanced speed. However, the inherent decay mechanism…
Unlocking the Secrets of Linear Complexity Sequence Model from A Unified Perspective
Zhen Qin, Xuyang Shen, Dong Li +4
We present the Linear Complexity Sequence Model (LCSM), a comprehensive solution that unites various sequence modeling techniques with linear complexity, including linear attention…
TAVGBench: Benchmarking Text to Audible-Video Generation
Yuxin Mao, Xuyang Shen, Jing Zhang +5
The Text to Audible-Video Generation (TAVG) task involves generating videos with accompanying audio based on text descriptions. Achieving this requires skillful alignment of both a…
HGRN2: Gated Linear RNNs with State Expansion
Zhen Qin, Songlin Yang, Weixuan Sun +4
Hierarchically gated linear RNN (HGRN, \citealt{HGRN}) has demonstrated competitive training speed and performance in language modeling while offering efficient inference. However,…
Linear Attention Sequence Parallelism
Weigao Sun, Zhen Qin, Dong Li +3
Sequence parallelism (SP) serves as a prevalent strategy to handle long sequences that exceed the memory limit of a single device. However, for linear sequence modeling methods lik…
CO2: Efficient Distributed Training with Full Communication-Computation Overlap
Weigao Sun, Zhen Qin, Weixuan Sun +5
The fundamental success of large language models hinges upon the efficacious implementation of large-scale distributed training techniques. Nevertheless, building a vast, high-perf…
Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
Zhen Qin, Weigao Sun, Dong Li +3
Linear attention is an efficient attention mechanism that has recently emerged as a promising alternative to conventional softmax attention. With its ability to process tokens in l…
Accelerating Toeplitz Neural Network with Constant-time Inference Complexity
Zhen Qin, Yiran Zhong
Toeplitz Neural Networks (TNNs) have exhibited outstanding performance in various sequence modeling tasks. They outperform commonly used Transformer-based models while benefiting f…
Hierarchically Gated Recurrent Neural Network for Sequence Modeling
Zhen Qin, Songlin Yang, Yiran Zhong
Transformers have surpassed RNNs in popularity due to their superior abilities in parallel training and long-term dependency modeling. Recently, there has been a renewed interest i…
All-pairs Consistency Learning for Weakly Supervised Semantic Segmentation
Weixuan Sun, Yanhao Zhang, Zhen Qin +5
In this work, we propose a new transformer-based regularization to better localize objects for Weakly supervised semantic segmentation (WSSS). In image-level WSSS, Class Activation…
Linearized Relative Positional Encoding
Zhen Qin, Weixuan Sun, Kaiyue Lu +6
Relative positional encoding is widely used in vanilla and linear transformers to represent positional information. However, existing encoding methods of a vanilla transformer are…
TransNormerLLM: A Faster and Better Large Language Model with Improved TransNormer
Zhen Qin, Dong Li, Weigao Sun +8
We present TransNormerLLM, the first linear attention-based Large Language Model (LLM) that outperforms conventional softmax attention-based models in terms of both accuracy and ef…
Exploring Transformer Extrapolation
Zhen Qin, Yiran Zhong, Hui Deng
Length extrapolation has attracted considerable attention recently since it allows transformers to be tested on longer sequences than those used in training. Previous research has…
Toeplitz Neural Network for Sequence Modeling
Zhen Qin, Xiaodong Han, Weixuan Sun +6
Sequence modeling has important applications in natural language processing and computer vision. Recently, the transformer-based models have shown strong performance on various seq…
Fine-grained Audible Video Description
Xuyang Shen, Dong Li, Jinxing Zhou +9
We explore a new task for audio-visual-language modeling called fine-grained audible video description (FAVD). It aims to provide detailed textual descriptions for the given audibl…
The Devil in Linear Transformer
Zhen Qin, XiaoDong Han, Weixuan Sun +4
Linear transformers aim to reduce the quadratic space-time complexity of vanilla transformers. However, they usually suffer from degraded performances on various tasks and corpus.…
Linear Video Transformer with Feature Fixation
Kaiyue Lu, Zexiang Liu, Jianyuan Wang +8
Vision Transformers have achieved impressive performance in video classification, while suffering from the quadratic complexity caused by the Softmax attention mechanism. Some stud…
Neural Architecture Search on Efficient Transformers and Beyond
Zexiang Liu, Dong Li, Kaiyue Lu +4
Recently, numerous efficient Transformers have been proposed to reduce the quadratic computational complexity of standard Transformers caused by the Softmax attention. However, mos…