activity
20182026
most citedVanillaNet: the Power of Minimalism in Deep Learning

84 citations · 147 across the 28 of their papers we have counts for

collaborators
Showing 2024Show all

6 papers · 1 filter

cs.CV2024

Instruct-IPT: All-in-One Image Processing Transformer via Weight Modulation

Yuchuan Tian, Jianhong Han, Hanting Chen +5

Due to the unaffordable size and intensive computation costs of low-level vision models, All-in-One models that are designed to address a handful of low-level vision tasks simultan…

cs.CV2024

U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers

Yuchuan Tian, Zhijun Tu, Hanting Chen +3

Diffusion Transformers (DiTs) introduce the transformer architecture to diffusion tasks for latent-space image generation. With an isotropic architecture that chains a series of tr…

cs.CV20241 cited

Distilling Semantic Priors from SAM to Efficient Image Restoration Models

Quan Zhang, Xiaoyu Liu, Wei Li +6

In image restoration (IR), leveraging semantic priors from segmentation models has been a common approach to improve performance. The recent segment anything model (SAM) has emerge…

cs.CL2024

DiJiang: Efficient Large Language Models through Compact Kernelization

Hanting Chen, Zhicheng Liu, Xutao Wang +2

In an effort to reduce the computational load of Transformers, research on linear attention has gained significant momentum. However, the improvement strategies for attention mecha…

cs.CV20242 cited

IPT-V2: Efficient Image Processing Transformer using Hierarchical Attentions

Zhijun Tu, Kunpeng Du, Hanting Chen +4

Recent advances have demonstrated the powerful capability of transformer architecture in image restoration. However, our analysis indicates that existing transformerbased methods c…

cs.CV20241 cited

Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models

Jianyuan Guo, Hanting Chen, Chengcheng Wang +3

Recent advancements in large language models have sparked interest in their extraordinary and near-superhuman capabilities, leading researchers to explore methods for evaluating an…