Search Results for author: Aosong Feng

Found 14 papers, 7 papers with code

From Similarity to Superiority: Channel Clustering for Time Series Forecasting

no code implementations31 Mar 2024 Jialin Chen, Jan Eric Lenssen, Aosong Feng, Weihua Hu, Matthias Fey, Leandros Tassiulas, Jure Leskovec, Rex Ying

Motivated by our observation of a correlation between the time series model's performance boost against channel mixing and the intrinsic similarity on a pair of channels, we developed a novel and adaptable Channel Clustering Module (CCM).

Clustering Time Series +1

Solving General Noisy Inverse Problem via Posterior Sampling: A Policy Gradient Viewpoint

no code implementations15 Mar 2024 Haoyue Tang, Tian Xie, Aosong Feng, Hanyu Wang, Chenyang Zhang, Yang Bai

Solving image inverse problems (e. g., super-resolution and inpainting) requires generating a high fidelity image that matches the given input (the low-resolution image or the masked image).

Image Restoration Super-Resolution

An Item is Worth a Prompt: Versatile Image Editing with Disentangled Control

1 code implementation7 Mar 2024 Aosong Feng, Weikang Qiu, Jinbin Bai, Xiao Zhang, Zhen Dong, Kaicheng Zhou, Rex Ying, Leandros Tassiulas

Building on the success of text-to-image diffusion models (DPMs), image editing is an important application to enable human interaction with AI-generated content.


Efficient High-Resolution Time Series Classification via Attention Kronecker Decomposition

no code implementations7 Mar 2024 Aosong Feng, Jialin Chen, Juan Garza, Brooklyn Berry, Francisco Salazar, Yifeng Gao, Rex Ying, Leandros Tassiulas

The high-resolution time series classification problem is essential due to the increasing availability of detailed temporal data in various domains.

Time Series Time Series Classification

Leveraging Large Language Models for Concept Graph Recovery and Question Answering in NLP Education

1 code implementation22 Feb 2024 Rui Yang, Boming Yang, Sixun Ouyang, Tianwei She, Aosong Feng, Yuang Jiang, Freddy Lecue, Jinghui Lu, Irene Li

We assess LLMs' zero-shot performance in creating domain-specific concept graphs and introduce TutorQA, a new expert-verified NLP-focused benchmark for scientific graph reasoning and QA.

Question Answering Text Generation

Integrating View Conditions for Image Synthesis

1 code implementation24 Oct 2023 Jinbin Bai, Zhen Dong, Aosong Feng, Xiao Zhang, Tian Ye, Kaicheng Zhou

In the field of image processing, applying intricate semantic modifications within existing images remains an enduring challenge.

Image Generation Object

XDLM: Cross-lingual Diffusion Language Model for Machine Translation

no code implementations25 Jul 2023 Linyao Chen, Aosong Feng, Boming Yang, Zihui Li

Recently, diffusion models have excelled in image generation tasks and have also been applied to neural language processing (NLP) for controllable text generation.

Image Generation Language Modelling +3

HiPool: Modeling Long Documents Using Graph Neural Networks

1 code implementation5 May 2023 Irene Li, Aosong Feng, Dragomir Radev, Rex Ying

Encoding long sequences in Natural Language Processing (NLP) is a challenging problem.

Document Classification Sentence

Diffuser: Efficient Transformers with Multi-hop Attention Diffusion for Long Sequences

1 code implementation21 Oct 2022 Aosong Feng, Irene Li, Yuang Jiang, Rex Ying

Efficient Transformers have been developed for long sequence modeling, due to their subquadratic memory and time complexity.

Language Modelling text-classification +1

Adaptive Graph Spatial-Temporal Transformer Network for Traffic Flow Forecasting

1 code implementation9 Jul 2022 Aosong Feng, Leandros Tassiulas

Traffic flow forecasting on graphs has real-world applications in many fields, such as transportation system and computer networks.

KerGNNs: Interpretable Graph Neural Networks with Graph Kernels

1 code implementation3 Jan 2022 Aosong Feng, Chenyu You, Shiqiang Wang, Leandros Tassiulas

We also show that the trained graph filters in KerGNNs can reveal the local graph structures of the dataset, which significantly improves the model interpretability compared with conventional GNN models.

Graph Classification

MEGAN: Memory Enhanced Graph Attention Network for Space-Time Video Super-Resolution

no code implementations28 Oct 2021 Chenyu You, Lianyi Han, Aosong Feng, Ruihan Zhao, Hui Tang, Wei Fan

Space-time video super-resolution (STVSR) aims to construct a high space-time resolution video sequence from the corresponding low-frame-rate, low-resolution video sequence.

Graph Attention Space-time Video Super-resolution +1

Energy-efficient and Robust Cumulative Training with Net2Net Transformation

no code implementations2 Mar 2020 Aosong Feng, Priyadarshini Panda

We achieve this by first training a small network (with lesser parameters) on a small subset of the original dataset, and then gradually expanding the network using Net2Net transformation to train incrementally on larger subsets of the dataset.

Computational Efficiency

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