Search Results for author: Yuan Cheng

Found 35 papers, 13 papers with code

The Career Interests of Large Language Models

no code implementations11 Jul 2024 Meng Hua, Yuan Cheng, HengShu Zhu

This study focuses on the aspect of career interests by applying the Occupation Network's Interest Profiler short form to LLMs as if they were human participants and investigates their hypothetical career interests and competence, examining how these vary with language changes and model advancements.

Text Generation

I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models

no code implementations28 May 2024 Xing Hu, Yuan Cheng, Dawei Yang, Zhihang Yuan, Jiangyong Yu, Chen Xu, Sifan Zhou

Post-training quantization (PTQ) serves as a potent technique to accelerate the inference of large language models (LLMs).


AI2Apps: A Visual IDE for Building LLM-based AI Agent Applications

1 code implementation7 Apr 2024 Xin Pang, Zhucong Li, Jiaxiang Chen, Yuan Cheng, Yinghui Xu, Yuan Qi

We introduce AI2Apps, a Visual Integrated Development Environment (Visual IDE) with full-cycle capabilities that accelerates developers to build deployable LLM-based AI agent Applications.

AI Agent Management

Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation framework

1 code implementation17 Mar 2024 Kaiyan Chang, Kun Wang, Nan Yang, Ying Wang, Dantong Jin, Wenlong Zhu, Zhirong Chen, Cangyuan Li, Hao Yan, Yunhao Zhou, Zhuoliang Zhao, Yuan Cheng, Yudong Pan, Yiqi Liu, Mengdi Wang, Shengwen Liang, Yinhe Han, Huawei Li, Xiaowei Li

Our 13B model (ChipGPT-FT) has a pass rate improvement compared with GPT-3. 5 in Verilog generation and outperforms in EDA script (i. e., SiliconCompiler) generation with only 200 EDA script data.

Data Augmentation

Sample Complexity Characterization for Linear Contextual MDPs

no code implementations5 Feb 2024 Junze Deng, Yuan Cheng, Shaofeng Zou, Yingbin Liang

Our result for the second model is the first-known result for such a type of function approximation models.

SNP-S3: Shared Network Pre-training and Significant Semantic Strengthening for Various Video-Text Tasks

1 code implementation31 Jan 2024 Xingning Dong, Qingpei Guo, Tian Gan, Qing Wang, Jianlong Wu, Xiangyuan Ren, Yuan Cheng, Wei Chu

By employing one shared BERT-type network to refine textual and cross-modal features simultaneously, SNP is lightweight and could support various downstream applications.


Knowledge-enhanced Multi-perspective Video Representation Learning for Scene Recognition

no code implementations9 Jan 2024 Xuzheng Yu, Chen Jiang, Wei zhang, Tian Gan, Linlin Chao, Jianan Zhao, Yuan Cheng, Qingpei Guo, Wei Chu

With the explosive growth of video data in real-world applications, a comprehensive representation of videos becomes increasingly important.

Representation Learning Scene Recognition

Large Language Models are Not Stable Recommender Systems

no code implementations25 Dec 2023 TianHui Ma, Yuan Cheng, HengShu Zhu, Hui Xiong

With the significant successes of large language models (LLMs) in many natural language processing tasks, there is growing interest among researchers in exploring LLMs for novel recommender systems.

Recommendation Systems

SemiSAM: Exploring SAM for Enhancing Semi-Supervised Medical Image Segmentation with Extremely Limited Annotations

no code implementations11 Dec 2023 Yichi Zhang, Yuan Cheng, Yuan Qi

Semi-supervised learning has attracted much attention due to its less dependence on acquiring abundant annotations from experts compared to fully supervised methods, which is especially important for medical image segmentation which typically requires intensive pixel/voxel-wise labeling by domain experts.

Image Segmentation Segmentation +2

Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes

no code implementations20 Oct 2023 Ruiquan Huang, Yuan Cheng, Jing Yang, Vincent Tan, Yingbin Liang

To this end, we posit a joint model class for tasks and use the notion of $\eta$-bracketing number to quantify its complexity; this number also serves as a general metric to capture the similarity of tasks and thus determines the benefit of multi-task over single-task RL.

Decision Making Multi-Task Learning +1

In-Context Convergence of Transformers

no code implementations8 Oct 2023 Yu Huang, Yuan Cheng, Yingbin Liang

For data with balanced features, we establish the finite-time convergence guarantee with near-zero prediction error by navigating our analysis over two phases of the training dynamics of the attention map.

In-Context Learning

Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning

1 code implementation20 Sep 2023 Chen Jiang, Hong Liu, Xuzheng Yu, Qing Wang, Yuan Cheng, Jia Xu, Zhongyi Liu, Qingpei Guo, Wei Chu, Ming Yang, Yuan Qi

We thereby present a new Triplet Partial Margin Contrastive Learning (TPM-CL) module to construct partial order triplet samples by automatically generating fine-grained hard negatives for matched text-video pairs.

Contrastive Learning Retrieval +3

Learning Segment Similarity and Alignment in Large-Scale Content Based Video Retrieval

no code implementations20 Sep 2023 Chen Jiang, Kaiming Huang, Sifeng He, Xudong Yang, Wei zhang, Xiaobo Zhang, Yuan Cheng, Lei Yang, Qing Wang, Furong Xu, Tan Pan, Wei Chu

SSAN is based on two newly proposed modules in video retrieval: (1) An efficient Self-supervised Keyframe Extraction (SKE) module to reduce redundant frame features, (2) A robust Similarity Pattern Detection (SPD) module for temporal alignment.

Retrieval Video Retrieval

FuXi: A cascade machine learning forecasting system for 15-day global weather forecast

2 code implementations22 Jun 2023 Lei Chen, Xiaohui Zhong, Feng Zhang, Yuan Cheng, Yinghui Xu, Yuan Qi, Hao Li

Over the past few years, due to the rapid development of machine learning (ML) models for weather forecasting, state-of-the-art ML models have shown superior performance compared to the European Centre for Medium-Range Weather Forecasts (ECMWF)'s high-resolution forecast (HRES) in 10-day forecasts at a spatial resolution of 0. 25 degree.

Weather Forecasting

Boundary-aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval

1 code implementation CVPR 2023 Tan Pan, Furong Xu, Xudong Yang, Sifeng He, Chen Jiang, Qingpei Guo, Feng Qian Xiaobo Zhang, Yuan Cheng, Lei Yang, Wei Chu

For traditional model upgrades, the old model will not be replaced by the new one until the embeddings of all the images in the database are re-computed by the new model, which takes days or weeks for a large amount of data.

Image Retrieval Retrieval

Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs

no code implementations20 Mar 2023 Yuan Cheng, Ruiquan Huang, Jing Yang, Yingbin Liang

In this work, we first provide the first known sample complexity lower bound that holds for any algorithm under low-rank MDPs.

reinforcement-learning Reinforcement Learning (RL) +1

DC-Former: Diverse and Compact Transformer for Person Re-Identification

1 code implementation28 Feb 2023 Wen Li, Cheng Zou, Meng Wang, Furong Xu, Jianan Zhao, Ruobing Zheng, Yuan Cheng, Wei Chu

In this paper, we propose a Diverse and Compact Transformer (DC-Former) that can achieve a similar effect by splitting embedding space into multiple diverse and compact subspaces.

Person Re-Identification

3D Pose Based Feedback for Physical Exercises

1 code implementation5 Aug 2022 Ziyi Zhao, Sena Kiciroglu, Hugues Vinzant, Yuan Cheng, Isinsu Katircioglu, Mathieu Salzmann, Pascal Fua

To evaluate our approach, we introduce a dataset with 3 different physical exercises.

Solutions for Fine-grained and Long-tailed Snake Species Recognition in SnakeCLEF 2022

no code implementations4 Jul 2022 Cheng Zou, Furong Xu, Meng Wang, Wen Li, Yuan Cheng

Automatic snake species recognition is important because it has vast potential to help lower deaths and disabilities caused by snakebites.

Self-Supervised Learning

Provable Benefit of Multitask Representation Learning in Reinforcement Learning

no code implementations13 Jun 2022 Yuan Cheng, Songtao Feng, Jing Yang, Hong Zhang, Yingbin Liang

To the best of our knowledge, this is the first theoretical study that characterizes the benefit of representation learning in exploration-based reward-free multitask RL for both upstream and downstream tasks.

Offline RL reinforcement-learning +2

Multi-modal Emotion Estimation for in-the-wild Videos

no code implementations24 Mar 2022 Liyu Meng, Yuchen Liu, Xiaolong Liu, Zhaopei Huang, Yuan Cheng, Meng Wang, Chuanhe Liu, Qin Jin

In this paper, we briefly introduce our submission to the Valence-Arousal Estimation Challenge of the 3rd Affective Behavior Analysis in-the-wild (ABAW) competition.

Arousal Estimation

Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation

1 code implementation CVPR 2022 Xingning Dong, Tian Gan, Xuemeng Song, Jianlong Wu, Yuan Cheng, Liqiang Nie

Scene Graph Generation, which generally follows a regular encoder-decoder pipeline, aims to first encode the visual contents within the given image and then parse them into a compact summary graph.

Decoder Graph Generation +1

Hyperspectral Imaging for cherry tomato

no code implementations10 Mar 2022 Yun Xiang, Qijun Chen, Zhongjin Su, Lu Zhang, Zuohui Chen, Guozhi Zhou, Zhuping Yao, Qi Xuan, Yuan Cheng

Cherry tomato (Solanum Lycopersicum) is popular with consumers over the world due to its special flavor.


HBReID: Harder Batch for Re-identification

no code implementations9 Dec 2021 Wen Li, Furong Xu, Jianan Zhao, Ruobing Zheng, Cheng Zou, Meng Wang, Yuan Cheng

Triplet loss is a widely adopted loss function in ReID task which pulls the hardest positive pairs close and pushes the hardest negative pairs far away.

Person Re-Identification

Discrimination-Aware Mechanism for Fine-Grained Representation Learning

no code implementations CVPR 2021 Furong Xu, Meng Wang, Wei zhang, Yuan Cheng, Wei Chu

Therefore, there is a need for a training mechanism that enforces the discriminativeness of all the elements in the feature to capture more the subtle visual cues.

Representation Learning Retrieval

Looking at CTR Prediction Again: Is Attention All You Need?

1 code implementation12 May 2021 Yuan Cheng, Yanbo Xue

Click-through rate (CTR) prediction is a critical problem in web search, recommendation systems and online advertisement displaying.

Click-Through Rate Prediction Recommendation Systems

HOTCAKE: Higher Order Tucker Articulated Kernels for Deeper CNN Compression

no code implementations28 Feb 2020 Rui Lin, Ching-Yun Ko, Zhuolun He, Cong Chen, Yuan Cheng, Hao Yu, Graziano Chesi, Ngai Wong

The emerging edge computing has promoted immense interests in compacting a neural network without sacrificing much accuracy.

Edge-computing Tensor Decomposition

Early Predictions for Medical Crowdfunding: A Deep Learning Approach Using Diverse Inputs

no code implementations9 Nov 2019 Tong Wang, Fujie Jin, Yu, Hu, Yuan Cheng

The prediction model and the interpretable insights can be applied to assist fundraisers with better promoting their fundraising campaigns and can potentially help crowdfunding platforms to provide more timely feedback to all fundraisers.

Clustering Time Series +1

DEEPEYE: A Compact and Accurate Video Comprehension at Terminal Devices Compressed with Quantization and Tensorization

no code implementations21 May 2018 Yuan Cheng, Guangya Li, Hai-Bao Chen, Sheldon X. -D. Tan, Hao Yu

As it requires a huge number of parameters when exposed to high dimensional inputs in video detection and classification, there is a grand challenge to develop a compact yet accurate video comprehension at terminal devices.

Action Recognition General Classification +5

Event-Radar: Real-time Local Event Detection System for Geo-Tagged Tweet Streams

1 code implementation19 Aug 2017 Sibo Zhang, Yuan Cheng, Deyuan Ke

The local event detection is to use posting messages with geotags on social networks to reveal the related ongoing events and their locations.

Event Detection

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