About Me 👨‍🔬

I am currently an Assistant Professor at the Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), affiliated with Shenzhen University.

My current research interests🔬 focus on:

• RWKV: a novel neural network architecture for language modeling
• Visual-Language Models combining visual and textual understanding

If you’re interested in academic collaboration, feel free to email me — I’d love to connect! We’re also recruiting interns — reach out if you’re passionate about AI! ✉️🚀

I have published 20+ papers at the top international AI conferences such as EMNLP, COLING, COLM.

Work Experience

• 2023.08 - Now, Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Assistant Professor
• 2017.08 - 2022.11, Tencent ML Platform (Shenzhen, China), Applied Research Scientist

News 🔥

• 2025.03: 🎉 RWKV-UI is accepted by ICME 2025
• 2024.12: 🎉 VisualRWKV is accepted by COLING 2025, check out the chinese introduction video on Bilibili 🎬
• 2023.08: I join Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) as a Assistant Professor

Selected Publications 📝

COLING 2025

VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models
Haowen Hou and Peigen Zeng and Fei Ma and Fei Richard Yu

Code | Paper | Video | BibTeX

COLM 2025

RWKV-7 “Goose” with Expressive Dynamic State Evolution
Bo Peng, Ruichong Zhang, Daniel Goldstein, Eric Alcaide, Haowen Hou，et al.

Paper | HuggingFace | Code

ICME 2025

RWKV-UI: UI Understanding with Enhanced Perception and Reasoning
Jiaxi Yang, Haowen Hou

Paper

IEEE SPL

MLLM-TA: Leveraging Multimodal Large Language Models for Precise Temporal Video Grounding
Yi Liu, Haowen Hou(co-first author), Fei Ma, Shiguang Ni, Fei Richard Yu

Paper

EAAI

BagFormer: Better cross-modal retrieval via bag-wise interaction
Haowen Hou, Xiaopeng Yan, Yigeng Zhang

Paper

COLM 2024

Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence
Bo Peng, Eric Alcaide, Quentin Anthony, …, Haowen Hou, et al.

Paper | HuggingFace | Code

EMNLP 2023

RWKV: Reinventing RNNs for the Transformer Era
Bo Peng, Eric Alcaide, Quentin Anthony, …, Haowen Hou, et al.

Paper | HuggingFace | Code

Other Publications 📚

• arXiv RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Tasks Haowen Hou, Fei Ma, Binwen Bai, Xinxin Zhu, Fei Yu
• arXiv Enhancing and Accelerating Large Language Models via Instruction-Aware Contextual Compression Haowen Hou, F. Richard Yu
• ISCSLP 2021 Sams-Net: A Sliced Attention-based Neural Network for Music Source Separation, Tingle Li, Jiawei Chen, Haowen Hou, Ming Li
• AAAI 2021 Workshop Multimodal Product Identification: Submission to Watch and Buy 2021 Challenge, Jun Peng, Su Feng, Ya Wang, Haowen Hou, et al.

Projects 🏭

2022 E-Commerce Visual Language Pre-training

• Developed a large-scale (100M pairs) e-commerce visual-language pre-training model for enhanced product understanding.
• Proposed BagFormer, a dual encoder for cross-modal retrieval using bag-wise interaction and entity-aware text granularity. Achieved top recall with low latency.
• Ranked 1st in MUGE Challenge with BagFormer.

2021 WeChat Video Product Identification

• Led design & development of scalable video product ID pipeline: data processing, model training, inference acceleration, and deployment (TensorRT, Kubernetes, Pulsar).
• Led the development of major modules: multimodal video classification(ResNet-50, BERT, and NextVlad), product detection(YOLO-v5), product retrieval(Siamese Network), and product tagging(ALBEF+XGBoost).
• Boosted overall GSB by 12.37%, Top-3 GSB by 26%, contributing to WeChat Video reaching 500M DAU.
• Won 2nd place in the AAAI 2021 Watch and Buy Challenge.

2020 WeChat Pay Merchant Understanding

• Tagged 7.7M merchants with 370M high-quality tags using distant supervision and active learning.
• Modeled merchant-tag relations as a reading comprehension task using BERT + fine-grained entity types.
• Achieved 96.6% top-1 accuracy on head merchants and 89.0% overall.
• Improved pickup rate by 6.58% and usage rate by 0.28% (via A/B testing).

2019 WeChat Search Query Improvement

• Built relevant query recommendation system to improve search satisfaction.
• Constructed co-click query graphs (Hadoop), filtered with FastText, trained DSSM with hard negatives, and deployed FAISS PQ Index for real-time similarity search (latency < 100ms).
• Led to 4.5% daily query view increase, raising search ad revenue by 3%.

Honors and Awards 🎖

• 2018, Shenzhen High-Level Overseas Talent
• 2013, NUS SMA3 Scholarship
• 2012, NUS NGS Scholarship
• 2007, First Prize, National Olympiad in Chemistry in Provinces (Top 1%)

Educations 📖

• 2013.01 - 2017.05, Ph.D., National University of Singapore, Singapore.
• 2008.08 - 2012.07, B.Eng., Harbin Institute of Technology, Harbin.

Invited Talks 💬

• 2025.03, RWKV: Next-Gen Model Architecture, NVIDIA GTC 2025
• 2024.12, RWKV: Next-Gen Model Architecture, Future Medicine Conference
• 2024.10, RWKV: Next-Gen Model Architecture, China National Conference on Social Media Processing 2024

Teaching 🧑‍🏫

• 2024 Fall Advanced Algorithms

Academic Service 🎓

• 2024.06 - Now, Journal Reviewer, IEEE Signal Processing Letters
• 2025.01 - Now, Conference Reviewer, IEEE International Conference on Multimedia & Expo (ICME)