Picture for Haowen Hou

Haowen Hou

VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models

Add code
Jun 19, 2024
Viaarxiv icon

Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence

Add code
Apr 10, 2024
Viaarxiv icon

RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Tasks

Add code
Jan 17, 2024
Viaarxiv icon

Revisit Human-Scene Interaction via Space Occupancy

Add code
Dec 05, 2023
Viaarxiv icon

RWKV: Reinventing RNNs for the Transformer Era

Add code
May 22, 2023
Figure 1 for RWKV: Reinventing RNNs for the Transformer Era
Figure 2 for RWKV: Reinventing RNNs for the Transformer Era
Figure 3 for RWKV: Reinventing RNNs for the Transformer Era
Figure 4 for RWKV: Reinventing RNNs for the Transformer Era
Viaarxiv icon

BagFormer: Better Cross-Modal Retrieval via bag-wise interaction

Add code
Dec 29, 2022
Figure 1 for BagFormer: Better Cross-Modal Retrieval via bag-wise interaction
Figure 2 for BagFormer: Better Cross-Modal Retrieval via bag-wise interaction
Figure 3 for BagFormer: Better Cross-Modal Retrieval via bag-wise interaction
Figure 4 for BagFormer: Better Cross-Modal Retrieval via bag-wise interaction
Viaarxiv icon

TF-Attention-Net: An End To End Neural Network For Singing Voice Separation

Add code
Oct 24, 2019
Figure 1 for TF-Attention-Net: An End To End Neural Network For Singing Voice Separation
Figure 2 for TF-Attention-Net: An End To End Neural Network For Singing Voice Separation
Figure 3 for TF-Attention-Net: An End To End Neural Network For Singing Voice Separation
Figure 4 for TF-Attention-Net: An End To End Neural Network For Singing Voice Separation
Viaarxiv icon