Search Results for author: Aojun Zhou

Found 36 papers, 23 papers with code

ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation

1 code implementation27 May 2024 Houxing Ren, Mingjie Zhan, Zhongyuan Wu, Aojun Zhou, Junting Pan, Hongsheng Li

Inspired by this, we present ReflectionCoder, a novel approach that effectively leverages reflection sequences constructed by integrating compiler feedback to improve one-off code generation performance.

Code Generation Mathematical Reasoning

SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models

1 code implementation25 May 2024 Xudong Lu, Aojun Zhou, Yuhui Xu, Renrui Zhang, Peng Gao, Hongsheng Li

Large Language Models (LLMs) have become pivotal in advancing the field of artificial intelligence, yet their immense sizes pose significant challenges for both fine-tuning and deployment.

TerDiT: Ternary Diffusion Models with Transformers

1 code implementation23 May 2024 Xudong Lu, Aojun Zhou, Ziyi Lin, Qi Liu, Yuhui Xu, Renrui Zhang, Yafei Wen, Shuai Ren, Peng Gao, Junchi Yan, Hongsheng Li

Recent developments in large-scale pre-trained text-to-image diffusion models have significantly improved the generation of high-fidelity images, particularly with the emergence of diffusion models based on transformer architecture (DiTs).

Image Generation Quantization

MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs

no code implementations26 Feb 2024 Zimu Lu, Aojun Zhou, Houxing Ren, Ke Wang, Weikang Shi, Junting Pan, Mingjie Zhan, Hongsheng Li

We augment the ground-truth solutions of our seed data and train a back-translation model to translate the augmented solutions back into new questions.

GSM8K Math +1

Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models

1 code implementation22 Feb 2024 Xudong Lu, Qi Liu, Yuhui Xu, Aojun Zhou, Siyuan Huang, Bo Zhang, Junchi Yan, Hongsheng Li

Specifically, we propose, for the first time to our best knowledge, post-training approaches for task-agnostic and task-specific expert pruning and skipping of MoE LLMs, tailored to improve deployment efficiency while maintaining model performance across a wide range of tasks.

NOAH: Learning Pairwise Object Category Attentions for Image Classification

1 code implementation4 Feb 2024 Chao Li, Aojun Zhou, Anbang Yao

We observe that the head structures of mainstream DNNs adopt a similar feature encoding pipeline, exploiting global feature dependencies while disregarding local ones.

Classification Multi-Label Image Classification +1

Integrating Large Language Models into Recommendation via Mutual Augmentation and Adaptive Aggregation

no code implementations25 Jan 2024 Sichun Luo, Yuxuan Yao, Bowei He, Yinya Huang, Aojun Zhou, Xinyi Zhang, Yuanzhang Xiao, Mingjie Zhan, Linqi Song

Conventional recommendation methods have achieved notable advancements by harnessing collaborative or sequential information from user behavior.

Data Augmentation

RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendation

1 code implementation26 Dec 2023 Sichun Luo, Bowei He, Haohan Zhao, Wei Shao, Yanlin Qi, Yinya Huang, Aojun Zhou, Yuxuan Yao, Zongpeng Li, Yuanzhang Xiao, Mingjie Zhan, Linqi Song

Large Language Models (LLMs) have demonstrated remarkable capabilities and have been extensively deployed across various domains, including recommender systems.

In-Context Learning Language Modelling +3

MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning

1 code implementation5 Oct 2023 Ke Wang, Houxing Ren, Aojun Zhou, Zimu Lu, Sichun Luo, Weikang Shi, Renrui Zhang, Linqi Song, Mingjie Zhan, Hongsheng Li

In this paper, we present a method to fine-tune open-source language models, enabling them to use code for modeling and deriving math equations and, consequently, enhancing their mathematical reasoning abilities.

Ranked #4 on Math Word Problem Solving on SVAMP (using extra training data)

Arithmetic Reasoning GSM8K +2

Efficient N:M Sparse DNN Training Using Algorithm, Architecture, and Dataflow Co-Design

no code implementations22 Sep 2023 Chao Fang, Wei Sun, Aojun Zhou, Zhongfeng Wang

At the algorithm level, a bidirectional weight pruning method, dubbed BDWP, is proposed to leverage the N:M sparsity of weights during both forward and backward passes of DNN training, which can significantly reduce the computational cost while maintaining model accuracy.

Computational Efficiency Scheduling

Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification

1 code implementation15 Aug 2023 Aojun Zhou, Ke Wang, Zimu Lu, Weikang Shi, Sichun Luo, Zipeng Qin, Shaoqing Lu, Anya Jia, Linqi Song, Mingjie Zhan, Hongsheng Li

We found that its success can be largely attributed to its powerful skills in generating and executing code, evaluating the output of code execution, and rectifying its solution when receiving unreasonable outputs.

Arithmetic Reasoning Math +1

LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model

3 code implementations28 Apr 2023 Peng Gao, Jiaming Han, Renrui Zhang, Ziyi Lin, Shijie Geng, Aojun Zhou, Wei zhang, Pan Lu, Conghui He, Xiangyu Yue, Hongsheng Li, Yu Qiao

This strategy effectively alleviates the interference between the two tasks of image-text alignment and instruction following and achieves strong multi-modal reasoning with only a small-scale image-text and instruction dataset.

Instruction Following Optical Character Recognition (OCR) +7

SparseMAE: Sparse Training Meets Masked Autoencoders

no code implementations ICCV 2023 Aojun Zhou, Yang Li, Zipeng Qin, Jianbo Liu, Junting Pan, Renrui Zhang, Rui Zhao, Peng Gao, Hongsheng Li

In this paper, we aim to reduce model complexity from large vision transformers pretrained by MAE with assistant of sparse training.

Omni-Dimensional Dynamic Convolution

1 code implementation ICLR 2022 Chao Li, Aojun Zhou, Anbang Yao

Learning a single static convolutional kernel in each convolutional layer is the common training paradigm of modern Convolutional Neural Networks (CNNs).

An Algorithm-Hardware Co-Optimized Framework for Accelerating N:M Sparse Transformers

no code implementations12 Aug 2022 Chao Fang, Aojun Zhou, Zhongfeng Wang

(1) From algorithm perspective, we propose a sparsity inheritance mechanism along with an inherited dynamic pruning (IDP) method to obtain a series of N:M sparse candidate Transformers rapidly.

Computational Efficiency Model Compression

Group R-CNN for Weakly Semi-supervised Object Detection with Points

1 code implementation CVPR 2022 Shilong Zhang, Zhuoran Yu, Liyang Liu, Xinjiang Wang, Aojun Zhou, Kai Chen

The core of this task is to train a point-to-box regressor on well-labeled images that can be used to predict credible bounding boxes for each point annotation.

Object Detection Representation Learning +1

Pyramid Fusion Transformer for Semantic Segmentation

no code implementations11 Jan 2022 Zipeng Qin, Jianbo Liu, Xiaolin Zhang, Maoqing Tian, Aojun Zhou, Shuai Yi, Hongsheng Li

The recently proposed MaskFormer gives a refreshed perspective on the task of semantic segmentation: it shifts from the popular pixel-level classification paradigm to a mask-level classification method.

Decoder Segmentation +1

DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks

1 code implementation NeurIPS 2021 Wei Sun, Aojun Zhou, Sander Stuijk, Rob Wijnhoven, Andrew Oakleigh Nelson, Hongsheng Li, Henk Corporaal

However, the existing N:M algorithms only address the challenge of how to train N:M sparse neural networks in a uniform fashion (i. e. every layer has the same N:M sparsity) and suffer from a significant accuracy drop for high sparsity (i. e. when sparsity > 80\%).

Network Pruning

Incorporating Convolution Designs into Visual Transformers

3 code implementations ICCV 2021 Kun Yuan, Shaopeng Guo, Ziwei Liu, Aojun Zhou, Fengwei Yu, Wei Wu

Motivated by the success of Transformers in natural language processing (NLP) tasks, there emerge some attempts (e. g., ViT and DeiT) to apply Transformers to the vision domain.

Image Classification

Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch

4 code implementations ICLR 2021 Aojun Zhou, Yukun Ma, Junnan Zhu, Jianbo Liu, Zhijie Zhang, Kun Yuan, Wenxiu Sun, Hongsheng Li

In this paper, we are the first to study training from scratch an N:M fine-grained structured sparse network, which can maintain the advantages of both unstructured fine-grained sparsity and structured coarse-grained sparsity simultaneously on specifically designed GPUs.

Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization

no code implementations31 Aug 2019 Zhuoran Yu, Aojun Zhou, Yukun Ma, Yudian Li, Xiaohan Zhang, Ping Luo

Experiment results show that SCT improves accuracy of single Resnet-50 on ImageNet by 1. 7% and 11. 5% accuracy when testing on image sizes of 224 and 128 respectively.

Data Augmentation Image Classification +1

HBONet: Harmonious Bottleneck on Two Orthogonal Dimensions

1 code implementation ICCV 2019 Duo Li, Aojun Zhou, Anbang Yao

MobileNets, a class of top-performing convolutional neural network architectures in terms of accuracy and efficiency trade-off, are increasingly used in many resourceaware vision applications.

object-detection Object Detection +2

Deeply-supervised Knowledge Synergy

1 code implementation CVPR 2019 Dawei Sun, Anbang Yao, Aojun Zhou, Hao Zhao

Convolutional Neural Networks (CNNs) have become deeper and more complicated compared with the pioneering AlexNet.

General Classification Image Classification

Adversarial Robustness vs Model Compression, or Both?

1 code implementation29 Mar 2019 Shaokai Ye, Kaidi Xu, Sijia Liu, Jan-Henrik Lambrechts, huan zhang, Aojun Zhou, Kaisheng Ma, Yanzhi Wang, Xue Lin

Furthermore, this work studies two hypotheses about weight pruning in the conventional setting and finds that weight pruning is essential for reducing the network model size in the adversarial setting, training a small model from scratch even with inherited initialization from the large model cannot achieve both adversarial robustness and high standard accuracy.

Adversarial Robustness Model Compression +1

SnapQuant: A Probabilistic and Nested Parameterization for Binary Networks

no code implementations27 Sep 2018 Kuan Wang, Hao Zhao, Anbang Yao, Aojun Zhou, Dawei Sun, Yurong Chen

During the training phase, we generate binary weights on-the-fly since what we actually maintain is the policy network, and all the binary weights are used in a burn-after-reading style.

Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks

no code implementations CVPR 2018 Aojun Zhou, Anbang Yao, Kuan Wang, Yurong Chen

Through explicitly regularizing the loss perturbation and the weight approximation error in an incremental way, we show that such a new optimization method is theoretically reasonable and practically effective.


Deep Neural Network Compression with Single and Multiple Level Quantization

1 code implementation6 Mar 2018 Yuhui Xu, Yongzhuang Wang, Aojun Zhou, Weiyao Lin, Hongkai Xiong

In this paper, we propose two novel network quantization approaches, single-level network quantization (SLQ) for high-bit quantization and multi-level network quantization (MLQ) for extremely low-bit quantization (ternary). We are the first to consider the network quantization from both width and depth level.

Neural Network Compression Quantization

Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights

3 code implementations10 Feb 2017 Aojun Zhou, Anbang Yao, Yiwen Guo, Lin Xu, Yurong Chen

The weights in the other group are responsible to compensate for the accuracy loss from the quantization, thus they are the ones to be re-trained.


Cannot find the paper you are looking for? You can Submit a new open access paper.