no code implementations • 30 May 2025 • Wenxuan Shi, Haochen Tan, Chuqiao Kuang, Xiaoguang Li, Xiaozhe Ren, Chen Zhang, Hanting Chen, Yasheng Wang, Lifeng Shang, Fisher Yu, Yunhe Wang
Building on this dataset, we propose DeepDiver, a Reinforcement Learning (RL) framework that promotes SIS by encouraging adaptive search policies through exploration under a real-world open-web environment.
no code implementations • 28 May 2025 • Hanting Chen, Yasheng Wang, Kai Han, Dong Li, Lin Li, Zhenni Bi, Jinpeng Li, Haoyu Wang, Fei Mi, Mingjian Zhu, Bin Wang, Kaikai Song, Yifei Fu, Xu He, Yu Luo, Chong Zhu, Quan He, Xueyu Wu, wei he, Hailin Hu, Yehui Tang, DaCheng Tao, Xinghao Chen, Yunhe Wang
This work presents Pangu Embedded, an efficient Large Language Model (LLM) reasoner developed on Ascend Neural Processing Units (NPUs), featuring flexible fast and slow thinking capabilities.
no code implementations • 26 May 2025 • Hanting Chen, Jiarui Qin, Jialong Guo, Tao Yuan, Yichun Yin, HuiLing Zhen, Yasheng Wang, Jinpeng Li, Xiaojun Meng, Meng Zhang, Rongju Ruan, Zheyuan Bai, Yehui Tang, Can Chen, Xinghao Chen, Fisher Yu, Ruiming Tang, Yunhe Wang
While structured pruning offers a promising avenue for model compression, existing methods often struggle with the detrimental effects of aggressive, simultaneous width and depth reductions, leading to substantial performance degradation.
no code implementations • 8 May 2025 • Haizhen Xie, Kunpeng Du, Qiangyu Yan, Sen Lu, Jianhong Han, Hanting Chen, Hailin Hu, Jie Hu
We introduce a novel block, $\Psi$-DiT, which effectively guides the DiT to enhance image restoration.
no code implementations • 21 Apr 2025 • Miaomiao Cai, Simiao Li, Wei Li, Xudong Huang, Hanting Chen, Jie Hu, Yunhe Wang
Recent advances in diffusion models have improved Real-World Image Super-Resolution (Real-ISR), but existing methods lack human feedback integration, risking misalignment with human preference and may leading to artifacts, hallucinations and harmful content generation.
no code implementations • 19 Apr 2025 • Jing Han, Hanting Chen, Kai Han, Xiaomeng Huang, Yongyun Hu, Wenjun Xu, DaCheng Tao, Ping Zhang
With the rapid development of machine learning in recent years, many problems in meteorology can now be addressed using AI models.
no code implementations • 14 Apr 2025 • Rong Yao, Hailin Hu, Yifei Fu, Hanting Chen, Wenyi Fang, Fanyi Du, Kai Han, Yunhe Wang
In the realm of large language model (LLM), as the size of large models increases, it also brings higher training costs.
no code implementations • 24 Mar 2025 • Yuchuan Tian, Hanting Chen, Mengyu Zheng, Yuchen Liang, Chao Xu, Yunhe Wang
Representation Alignment (REPA) that aligns Diffusion Transformer (DiT) hidden-states with ViT visual encoders has proven highly effective in DiT training, demonstrating superior convergence properties, but it has not been validated on the canonical diffusion U-Net architecture that shows faster convergence compared to DiTs.
Ranked #15 on
Image Generation
on ImageNet 256x256
no code implementations • 24 Feb 2025 • Miaomiao Cai, Guanjie Wang, Wei Li, Zhijun Tu, Hanting Chen, Shaohui Lin, Jie Hu
In the field of autoregressive (AR) image generation, models based on the 'next-token prediction' paradigm of LLMs have shown comparable performance to diffusion models by reducing inductive biases.
no code implementations • 20 Feb 2025 • Haoyu Wang, Tong Teng, Tianyu Guo, An Xiao, Duyu Tang, Hanting Chen, Yunhe Wang
Handling long-context sequences efficiently remains a significant challenge in large language models (LLMs).
no code implementations • CVPR 2025 • Xin Ding, Lei Yu, Xin Li, Zhijun Tu, Hanting Chen, Jie Hu, Zhibo Chen
The RaSS is a plug-and-play module, which is applicable to multiple denoising diffusion samplers of diffusion models.
1 code implementation • CVPR 2025 • Yuchuan Tian, Jing Han, Chengcheng Wang, Yuchen Liang, Chao Xu, Hanting Chen
Diffusion models have shown exceptional performance in visual generation tasks.
no code implementations • 26 Sep 2024 • Yuchen Liang, Yuchuan Tian, Lei Yu, Huao Tang, Jie Hu, Xiangzhong Fang, Hanting Chen
The curvature of ODE trajectories in diffusion models hinders their ability to generate high-quality images in a few number of function evaluations (NFE).
1 code implementation • 14 Aug 2024 • Xiao He, Huaao Tang, Zhijun Tu, Junchao Zhang, Kun Cheng, Hanting Chen, Yong Guo, Mingrui Zhu, Nannan Wang, Xinbo Gao, Jie Hu
Specifically, we introduce a novel score distillation strategy to align the data distribution between the outputs of the student and teacher models after minor noise perturbation.
no code implementations • 15 Jul 2024 • Xianing Chen, Hanting Chen, Hailin Hu
Frequency domain representation of time series feature offers a concise representation for handling real-world time series data with inherent complexity and dynamic nature.
no code implementations • 14 Jul 2024 • Xiaoyu Liu, Yun Zhang, Wei Li, Simiao Li, Xudong Huang, Hanting Chen, Yehui Tang, Jie Hu, Zhiwei Xiong, Yunhe Wang
At the sequence level, we propose a sequence correction and re-generation (SCRG) strategy.
1 code implementation • 30 Jun 2024 • Yuchuan Tian, Jianhong Han, Hanting Chen, Yuanyuan Xi, Ning Ding, Jie Hu, Chao Xu, Yunhe Wang
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 simultaneously have been popular.
Ranked #1 on
Single Image Desnowing
on CSD
1 code implementation • 24 Jun 2024 • Yirui Chen, Xudong Huang, Quan Zhang, Wei Li, Mingjian Zhu, Qiangyu Yan, Simiao Li, Hanting Chen, Hailin Hu, Jie Yang, Wei Liu, Jie Hu
The extraordinary ability of generative models emerges as a new trend in image editing and generating realistic images, posing a serious threat to the trustworthiness of multimedia data and driving the research of image manipulation detection and location (IMDL).
no code implementations • 22 May 2024 • Liyu Chen, Huaao Tang, Yi Wen, Hanting Chen, Wei Li, Junchao Liu, Jie Hu
To address these issues, we propose the Collaboration of Teachers Framework (CTF), which consists of multiple pairs of teacher and student models for training.
1 code implementation • 4 May 2024 • Yuchuan Tian, Zhijun Tu, Hanting Chen, Jie Hu, Chao Xu, Yunhe Wang
Diffusion Transformers (DiTs) introduce the transformer architecture to diffusion tasks for latent-space image generation.
1 code implementation • 9 Apr 2024 • Junbo Qiao, Wei Li, Haizhen Xie, Hanting Chen, Yunshuai Zhou, Zhijun Tu, Jie Hu, Shaohui Lin
Extensive experiments on multiple image processing tasks (e. g., image super-resolution (SR), JPEG artifact reduction, and image denoising) demonstrate the superiority of LIPT on both latency and PSNR.
no code implementations • 3 Apr 2024 • Simiao Li, Yun Zhang, Wei Li, Hanting Chen, Wenjia Wang, BingYi Jing, Shaohui Lin, Jie Hu
Knowledge distillation (KD) is a promising yet challenging model compression technique that transfers rich learning representations from a well-performing but cumbersome teacher model to a compact student model.
no code implementations • 31 Mar 2024 • Zhijun Tu, Kunpeng Du, Hanting Chen, Hailing Wang, Wei Li, Jie Hu, Yunhe Wang
Recent advances have demonstrated the powerful capability of transformer architecture in image restoration.
1 code implementation • 29 Mar 2024 • Hanting Chen, Zhicheng Liu, Xutao Wang, Yuchuan Tian, Yunhe Wang
In an effort to reduce the computational load of Transformers, research on linear attention has gained significant momentum.
no code implementations • CVPR 2024 • Quan Zhang, Xiaoyu Liu, Wei Li, Hanting Chen, Junchao Liu, Jie Hu, Zhiwei Xiong, Chun Yuan, Yunhe Wang
SPD leverages a self-distillation manner to distill the fused semantic priors to boost the performance of original IR models.
1 code implementation • 6 Feb 2024 • Jianyuan Guo, Hanting Chen, Chengcheng Wang, Kai Han, Chang Xu, Yunhe Wang
Recent advancements in large language models have sparked interest in their extraordinary and near-superhuman capabilities, leading researchers to explore methods for evaluating and optimizing these abilities, which is called superalignment.
1 code implementation • CVPR 2024 • Yuchuan Tian, Hanting Chen, Chao Xu, Yunhe Wang
Alternatively we leverage the flexibility of graphs and propose the Image Processing GNN (IPG) model to break the rigidity that dominates previous SR methods.
Ranked #11 on
Image Super-Resolution
on Urban100 - 4x upscaling
no code implementations • 27 Dec 2023 • Yunhe Wang, Hanting Chen, Yehui Tang, Tianyu Guo, Kai Han, Ying Nie, Xutao Wang, Hailin Hu, Zheyuan Bai, Yun Wang, Fangcheng Liu, Zhicheng Liu, Jianyuan Guo, Sinan Zeng, Yinchen Zhang, Qinghua Xu, Qun Liu, Jun Yao, Chao Xu, DaCheng Tao
We then demonstrate that the proposed approach is significantly effective for enhancing the model nonlinearity through carefully designed ablations; thus, we present a new efficient model architecture for establishing modern, namely, PanGu-$\pi$.
no code implementations • 13 Dec 2023 • Xin Ding, Xiaoyu Liu, Zhijun Tu, Yun Zhang, Wei Li, Jie Hu, Hanting Chen, Yehui Tang, Zhiwei Xiong, Baoqun Yin, Yunhe Wang
Post-training quantization (PTQ) has played a key role in compressing large language models (LLMs) with ultra-low costs.
1 code implementation • 12 Dec 2023 • Mingjian Zhu, Hanting Chen, Mouxiao Huang, Wei Li, Hailin Hu, Jie Hu, Yunhe Wang
The misuse of AI imagery can have harmful societal effects, prompting the creation of detectors to combat issues like the spread of fake news.
1 code implementation • NeurIPS 2023 • Yuchuan Tian, Hanting Chen, Tianyu Guo, Chao Xu, Yunhe Wang
To this end, we propose a Rank-based PruninG (RPG) method to maintain the ranks of sparse weights in an adversarial manner.
no code implementations • 26 Sep 2023 • Hailing Wang, Wei Li, Yuanyuan Xi, Jie Hu, Hanting Chen, Longyu Li, Yunhe Wang
By matching similar patches between frames, objects with large motion ranges in dynamic scenes can be aligned, which can effectively alleviate the generation of artifacts.
1 code implementation • 25 Sep 2023 • Yun Zhang, Wei Li, Simiao Li, Hanting Chen, Zhijun Tu, Wenjia Wang, BingYi Jing, Shaohui Lin, Jie Hu
Knowledge distillation (KD) compresses deep neural networks by transferring task-related knowledge from cumbersome pre-trained teacher models to compact student models.
Ranked #32 on
Image Super-Resolution
on Urban100 - 4x upscaling
3 code implementations • 29 May 2023 • Yuchuan Tian, Hanting Chen, Xutao Wang, Zheyuan Bai, Qinghua Zhang, Ruifeng Li, Chao Xu, Yunhe Wang
Recent releases of Large Language Models (LLMs), e. g. ChatGPT, are astonishing at generating human-like texts, but they may impact the authenticity of texts.
5 code implementations • NeurIPS 2023 • Hanting Chen, Yunhe Wang, Jianyuan Guo, DaCheng Tao
In this study, we introduce VanillaNet, a neural network architecture that embraces elegance in design.
1 code implementation • CVPR 2023 • Xudong Huang, Wei Li, Jie Hu, Hanting Chen, Yunhe Wang
We present Reference-guided Super-Resolution Neural Radiance Field (RefSR-NeRF) that extends NeRF to super resolution and photorealistic novel view synthesis.
2 code implementations • CVPR 2023 • Zhijun Tu, Jie Hu, Hanting Chen, Yunhe Wang
In this paper, we study post-training quantization(PTQ) for image super resolution using only a few unlabeled calibration images.
4 code implementations • CVPR 2022 • Wenshuo Li, Hanting Chen, Jianyuan Guo, Ziyang Zhang, Yunhe Wang
However, due to the simplicity of their structures, the performance highly depends on the local features communication machenism.
4 code implementations • NeurIPS 2021 • Han Shu, Jiahao Wang, Hanting Chen, Lin Li, Yujiu Yang, Yunhe Wang
With the new operation, vision transformers constructed using additions can also provide powerful feature representations.
no code implementations • 29 Sep 2021 • Lin Xinyang, Hanting Chen, Yixing Xu, Chao Xu, Xiaolin Gui, Yiping Deng, Yunhe Wang
We study the problem of learning from positive and unlabeled (PU) data in the federated setting, where each client only labels a little part of their dataset due to the limitation of resources and time.
1 code implementation • 21 Jun 2021 • Xinyang Lin, Hanting Chen, Yixing Xu, Chao Xu, Xiaolin Gui, Yiping Deng, Yunhe Wang
We study the problem of learning from positive and unlabeled (PU) data in the federated setting, where each client only labels a little part of their dataset due to the limitation of resources and time.
1 code implementation • CVPR 2021 • Hanting Chen, Tianyu Guo, Chang Xu, Wenshuo Li, Chunjing Xu, Chao Xu, Yunhe Wang
Experiments on various datasets demonstrate that the student networks learned by the proposed method can achieve comparable performance with those using the original dataset.
no code implementations • CVPR 2021 • Yiman Zhang, Hanting Chen, Xinghao Chen, Yiping Deng, Chunjing Xu, Yunhe Wang
Experiments on various datasets and architectures demonstrate that the proposed method is able to be utilized for effectively learning portable student networks without the original data, e. g., with 0. 16dB PSNR drop on Set5 for x2 super resolution.
no code implementations • 29 May 2021 • Hanting Chen, Yunhe Wang, Chang Xu, Chao Xu, Chunjing Xu, Tong Zhang
The widely-used convolutions in deep neural networks are exactly cross-correlation to measure the similarity between input feature and convolution filters, which involves massive multiplications between float values.
no code implementations • 12 May 2021 • Wenshuo Li, Hanting Chen, Mingqiang Huang, Xinghao Chen, Chunjing Xu, Yunhe Wang
Adder neural network (AdderNet) is a new kind of deep model that replaces the original massive multiplications in convolutions by additions while preserving the high performance.
no code implementations • 25 Jan 2021 • Yunhe Wang, Mingqiang Huang, Kai Han, Hanting Chen, Wei zhang, Chunjing Xu, DaCheng Tao
With a comprehensive comparison on the performance, power consumption, hardware resource consumption and network generalization capability, we conclude the AdderNet is able to surpass all the other competitors including the classical CNN, novel memristor-network, XNOR-Net and the shift-kernel based network, indicating its great potential in future high performance and energy-efficient artificial intelligence applications.
no code implementations • 23 Dec 2020 • Kai Han, Yunhe Wang, Hanting Chen, Xinghao Chen, Jianyuan Guo, Zhenhua Liu, Yehui Tang, An Xiao, Chunjing Xu, Yixing Xu, Zhaohui Yang, Yiman Zhang, DaCheng Tao
Transformer, first applied to the field of natural language processing, is a type of deep neural network mainly based on the self-attention mechanism.
6 code implementations • CVPR 2021 • Hanting Chen, Yunhe Wang, Tianyu Guo, Chang Xu, Yiping Deng, Zhenhua Liu, Siwei Ma, Chunjing Xu, Chao Xu, Wen Gao
To maximally excavate the capability of transformer, we present to utilize the well-known ImageNet benchmark for generating a large amount of corrupted image pairs.
Ranked #1 on
Single Image Deraining
on Rain100L
(using extra training data)
no code implementations • CVPR 2021 • Dehua Song, Yunhe Wang, Hanting Chen, Chang Xu, Chunjing Xu, DaCheng Tao
To this end, we thoroughly analyze the relationship between an adder operation and the identity mapping and insert shortcuts to enhance the performance of SR models using adder networks.
no code implementations • CVPR 2020 • Hanting Chen, Yunhe Wang, Han Shu, Yehui Tang, Chunjing Xu, Boxin Shi, Chao Xu, Qi Tian, Chang Xu
This paper studies the compression and acceleration of 3-dimensional convolutional neural networks (3D CNNs).
no code implementations • CVPR 2020 • Yehui Tang, Yunhe Wang, Yixing Xu, Hanting Chen, Chunjing Xu, Boxin Shi, Chao Xu, Qi Tian, Chang Xu
A graph convolutional neural network is introduced to predict the performance of architectures based on the learned representations and their relation modeled by the graph.
no code implementations • 7 Mar 2020 • Hanting Chen, Yunhe Wang, Han Shu, Changyuan Wen, Chunjing Xu, Boxin Shi, Chao Xu, Chang Xu
To promote the capability of student generator, we include a student discriminator to measure the distances between real images, and images generated by student and teacher generators.
no code implementations • 3 Feb 2020 • Chuanjian Liu, Kai Han, Yunhe Wang, Hanting Chen, Qi Tian, Chunjing Xu
Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters.
7 code implementations • CVPR 2020 • Hanting Chen, Yunhe Wang, Chunjing Xu, Boxin Shi, Chao Xu, Qi Tian, Chang Xu
The widely-used convolutions in deep neural networks are exactly cross-correlation to measure the similarity between input feature and convolution filters, which involves massive multiplications between float values.
2 code implementations • NeurIPS 2019 • Yixing Xu, Yunhe Wang, Hanting Chen, Kai Han, Chunjing Xu, DaCheng Tao, Chang Xu
In practice, only a small portion of the original training set is required as positive examples and more useful training examples can be obtained from the massive unlabeled data on the cloud through a PU classifier with an attention based multi-scale feature extractor.
2 code implementations • ICCV 2019 • Han Shu, Yunhe Wang, Xu Jia, Kai Han, Hanting Chen, Chunjing Xu, Qi Tian, Chang Xu
Generative adversarial networks (GANs) have been successfully used for considerable computer vision tasks, especially the image-to-image translation.
3 code implementations • ICCV 2019 • Hanting Chen, Yunhe Wang, Chang Xu, Zhaohui Yang, Chuanjian Liu, Boxin Shi, Chunjing Xu, Chao Xu, Qi Tian
Learning portable neural networks is very essential for computer vision for the purpose that pre-trained heavy deep models can be well applied on edge devices such as mobile phones and micro sensors.
no code implementations • 17 Dec 2018 • Hanting Chen, Yunhe Wang, Chang Xu, Chao Xu, DaCheng Tao
Experiments on benchmark datasets and well-trained networks suggest that the proposed algorithm is superior to state-of-the-art teacher-student learning methods in terms of computational and storage complexity.