32 citations · 96 across the 18 of their papers we have counts for
19 papers
MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
Luyuan Zhang, Siyuan Li, Zedong Wang +7
Most visual tokenizers for image generation are bifurcated into two families with complementary limitations: continuous VAEs offer high-fidelity reconstruction but suffer from dens…
RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
Siyong Jian, Siyuan Li, Luyuan Zhang +5
Discrete autoregressive (AR) text-to-image (T2I) models pair a VQ tokenizer with an AR policy, and current post-training pipelines optimize only the policy while keeping the VQ dec…
CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing
Yucheng Wang, Zedong Wang, Yuetong Wu +2
Unified diffusion editors often rely on a fixed, shared backbone for diverse tasks, suffering from task interference and poor adaptation to heterogeneous demands (e.g., local vs gl…
Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning
Zedong Wang, Siyuan Li, Dan Xu
Despite the promise of Multi-Task Learning in leveraging complementary knowledge across tasks, existing multi-task optimization (MTO) techniques remain fixated on resolving conflic…
Taming LLMs by Scaling Learning Rates with Gradient Grouping
Siyuan Li, Juanxi Tian, Zedong Wang +4
Training large language models (LLMs) poses challenges due to their massive scale and heterogeneous architectures. While adaptive optimizers like AdamW help address gradient variat…
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
Siyuan Li, Luyuan Zhang, Zedong Wang +8
Masked Image Modeling (MIM) with Vector Quantization (VQ) has achieved great success in both self-supervised pre-training and image generation. However, most existing methods strug…
Prior-guided Hierarchical Harmonization Network for Efficient Image Dehazing
Xiongfei Su, Siyuan Li, Yuning Cui +7
Image dehazing is a crucial task that involves the enhancement of degraded images to recover their sharpness and textures. While vision Transformers have exhibited impressive resul…
Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
Siyuan Li, Juanxi Tian, Zedong Wang +6
This paper delves into the interplay between vision backbones and optimizers, unvealing an inter-dependent phenomenon termed \textit{\textbf{b}ackbone-\textbf{o}ptimizer \textbf{c}…
A Survey on Mixup Augmentations and Beyond
Xin Jin, Hongyu Zhu, Siyuan Li +6
As Deep Neural Networks have achieved thrilling breakthroughs in the past decade, data augmentations have garnered increasing attention as regularization techniques when massive la…
Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences
Zicheng Liu, Siyuan Li, Li Wang +3
To mitigate the computational complexity in the self-attention mechanism on long sequences, linear attention utilizes computation tricks to achieve linear complexity, while state s…
VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling
Siyuan Li, Zedong Wang, Zicheng Liu +5
Similar to natural language models, pre-trained genome language models are proposed to capture the underlying intricacies within genomes with unsupervised sequence modeling. They h…
LongVQ: Long Sequence Modeling with Vector Quantization on Structured Memory
Zicheng Liu, Li Wang, Siyuan Li +3
Transformer models have been successful in various sequence processing tasks, but the self-attention mechanism's computational cost limits its practicality for long sequences. Alth…
Switch EMA: A Free Lunch for Better Flatness and Sharpness
Siyuan Li, Zicheng Liu, Juanxi Tian +9
Exponential Moving Average (EMA) is a widely used weight averaging (WA) regularization to learn flat optima for better generalizations without extra cost in deep neural network (DN…
Masked Modeling for Self-supervised Representation Learning on Vision and Beyond
Siyuan Li, Luyuan Zhang, Zedong Wang +8
As the deep learning revolution marches on, self-supervised learning has garnered increasing attention in recent years thanks to its remarkable representation learning ability and…
SemiReward: A General Reward Model for Semi-supervised Learning
Siyuan Li, Weiyang Jin, Zedong Wang +4
Semi-supervised learning (SSL) has witnessed great progress with various improvements in the self-training framework with pseudo labeling. The main challenge is how to distinguish…
OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning
Cheng Tan, Siyuan Li, Zhangyang Gao +5
Spatio-temporal predictive learning is a learning paradigm that enables models to learn spatial and temporal patterns by predicting future frames from given past frames in an unsup…
MogaNet: Multi-order Gated Aggregation Network
Siyuan Li, Zedong Wang, Zicheng Liu +6
By contextualizing the kernel as global as possible, Modern ConvNets have shown great potential in computer vision tasks. However, recent progress on multi-order game-theoretic int…
OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning
Siyuan Li, Zedong Wang, Zicheng Liu +5
Mixup augmentation has emerged as a widely used technique for improving the generalization ability of deep neural networks (DNNs). However, the lack of standardized implementations…
Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup
Siyuan Li, Zicheng Liu, Zedong Wang +3
Mixup is a well-known data-dependent augmentation technique for DNNs, consisting of two sub-tasks: mixup generation and classification. However, the recent dominant online training…