Bowen Wu

Orcid: 0000-0002-9863-6896

Affiliations:
  • Tencent, China
  • Peking University, Beijing, China


According to our database1, Bowen Wu authored at least 16 papers between 2016 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
Empowering LLMs in Task-Oriented Dialogues: A Domain-Independent Multi-Agent Framework and Fine-Tuning Strategy.
CoRR, May, 2025

RAIDEN-R1: Improving Role-awareness of LLMs via GRPO with Verifiable Reward.
CoRR, May, 2025

Improving Generalization in Intent Detection: GRPO with Reward-Based Curriculum Sampling.
CoRR, April, 2025

F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimization.
CoRR, April, 2025

Interpersonal Memory Matters: A New Task for Proactive Dialogue Utilizing Conversational History.
CoRR, March, 2025

RAIDEN Benchmark: Evaluating Role-playing Conversational Agents with Measurement-Driven Custom Dialogues.
Proceedings of the 31st International Conference on Computational Linguistics, 2025

2022
Semorph: A Morphology Semantic Enhanced Pre-trained Model for Chinese Spam Text Detection.
Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022

2021
Learning to generate structured queries from natural language with indirect supervision.
Comput. Speech Lang., 2021

2020
Towards Non-task-specific Distillation of BERT via Sentence Representation Approximation.
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, 2020

Guiding Variational Response Generator to Exploit Persona.
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020

2019
MemeFaceGenerator: Adversarial Synthesis of Chinese Meme-face from Natural Sentences.
CoRR, 2019

Improving the Robustness of Deep Reading Comprehension Models by Leveraging Syntax Prior.
Proceedings of the 2nd Workshop on Machine Reading for Question Answering, 2019

2018
Why Do Neural Response Generation Models Prefer Universal Replies?
CoRR, 2018

LSDSCC: a Large Scale Domain-Specific Conversational Corpus for Response Generation with Diversity Oriented Evaluation Metrics.
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2018

A Prospective-Performance Network to Alleviate Myopia in Beam Search for Response Generation.
Proceedings of the 27th International Conference on Computational Linguistics, 2018

2016
Ranking Responses Oriented to Conversational Relevance in Chat-bots.
Proceedings of the COLING 2016, 2016


  Loading...