Guanglu Wan

58 papers A* 6A 7B 1C 1Misc 3Journal 28Unranked 12
YearRankTypeTitle / Venue / Authors
2026 J jnl
LongCat-AudioDiT: High-Fidelity Diffusion Text-to-Speech in the Waveform Latent Space.
CoRR
Detai Xin, Shujie Hu, Chengzuo Yang, Chen Huang, Guoqiao Yu, Guanglu Wan, Xunliang Cai
2025 — conf
AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models.
ACL (Findings)
Qi Liu, Jingqing Ruan, Hao Li, Haodong Zhao, Desheng Wang, Jiansong Chen, Guanglu Wan, Xunliang Cai, Zhi Zheng, Tong Xu
2025 J jnl
AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models.
CoRR
Qi Liu, Jingqing Ruan, Hao Li, Haodong Zhao, Desheng Wang, Jiansong Chen, Guanglu Wan, Xunliang Cai, Zhi Zheng, Tong Xu
2025 J jnl
Audio Turing Test: Benchmarking the Human-likeness of Large Language Model-based Text-to-Speech Systems in Chinese.
CoRR
Xihuai Wang, Ziyi Zhao, Siyu Ren, Shao Zhang, Song Li, Xiaoyu Li, Ziwen Wang, Lin Qiu, Guanglu Wan, Xuezhi Cao, Xunliang Cai, Weinan Zhang
2025 J jnl
LongCat-Audio-Codec: An Audio Tokenizer and Detokenizer Solution Designed for Speech Large Language Models.
CoRR
Xiaohan Zhao, Hongyu Xiang, Shengze Ye, Song Li, Zhengkun Tian, Guanyu Chen, Ke Ding, Guanglu Wan
2025 J jnl
MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning.
CoRR
Yueqian Wang, Songxiang Liu, Disong Wang, Nuo Xu, Guanglu Wan, Huishuai Zhang, Dongyan Zhao
2025 C conf
OOQ: Outlier-Oriented Quantization for Efficient Large Language Models.
ASRU
Haoyu Wang, Bei Liu, Hang Shao, Bo Xiao, Ke Zeng, Guanglu Wan, Yanmin Qian
2025 J jnl
Omni-AutoThink: Adaptive Multimodal Reasoning via Reinforcement Learning.
CoRR
Dongchao Yang, Songxiang Liu, Disong Wang, Yuanyuan Wang, Guanglu Wan, Helen Meng
2025 J jnl
UniComp: Rethinking Video Compression Through Informational Uniqueness.
CoRR
Chao Yuan, Shimin Chen, Minliang Lin, Limeng Qiao, Guanglu Wan, Lin Ma
2024 — conf
As-Speech: Adaptive Style For Speech Synthesis.
SLT
Zhipeng Li, Xiaofen Xing, Jun Wang, Shuaiqi Chen, Guoqiao Yu, Guanglu Wan, Xiangmin Xu
2024 J jnl
CLAQ: Pushing the Limits of Low-Bit Post-Training Quantization for LLMs.
CoRR
Haoyu Wang, Bei Liu, Hang Shao, Bo Xiao, Ke Zeng, Guanglu Wan, Yanmin Qian
2024 — conf
Dual-Stage Multi-Task Syntax-Oriented Pre-Training for Syntactically Controlled Paraphrase Generation.
ACL (Findings)
Hongxu Liu, Xiaojie Wang, Jiashen Sun, Ke Zeng, Guanglu Wan
2024 Misc conf
Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter.
ICASSP
Song Li, Yongbin You, Xuezhi Wang, Ke Ding, Guanglu Wan
2024 — conf
Learning or Self-aligning? Rethinking Instruction Fine-tuning.
ACL (1)
Mengjie Ren, Boxi Cao, Hongyu Lin, Cao Liu, Xianpei Han, Ke Zeng, Guanglu Wan, Xunliang Cai, Le Sun
2024 J jnl
Learning or Self-aligning? Rethinking Instruction Fine-tuning.
CoRR
Mengjie Ren, Boxi Cao, Hongyu Lin, Cao Liu, Xianpei Han, Ke Zeng, Guanglu Wan, Xunliang Cai, Le Sun
2024 A conf
MSR-86K: An Evolving, Multilingual Corpus with 86, 300 Hours of Transcribed Audio for Speech Recognition Research.
INTERSPEECH
Song Li, Yongbin You, Xuezhi Wang, Zhengkun Tian, Ke Ding, Guanglu Wan
2024 J jnl
MSR-86K: An Evolving, Multilingual Corpus with 86,300 Hours of Transcribed Audio for Speech Recognition Research.
CoRR
Song Li, Yongbin You, Xuezhi Wang, Zhengkun Tian, Ke Ding, Guanglu Wan
2024 — conf
Pattern Shifting or Knowledge Losing? A Forgetting Perspective for Understanding the Effect of Instruction Fine-Tuning.
CCL
Chunkang Zhang, Boxi Cao, Yaojie Lu, Hongyu Lin, Liu Cao, Ke Zeng, Guanglu Wan, Xunliang Cai, Xianpei Han, Le Sun
2023 — conf
A Task-Oriented Dialog Model with Task-Progressive and Policy-Aware Pre-training.
NLPCC (1)
Lucen Zhong, Hengtong Lu, Caixia Yuan, Xiaojie Wang, Jiashen Sun, Ke Zeng, Guanglu Wan
2023 J jnl
A Task-oriented Dialog Model with Task-progressive and Policy-aware Pre-training.
CoRR
Lucen Zhong, Hengtong Lu, Caixia Yuan, Xiaojie Wang, Jiashen Sun, Ke Zeng, Guanglu Wan
2023 — conf
Ambiguous Learning from Retrieval: Towards Zero-shot Semantic Parsing.
ACL (1)
Shan Wu, Chunlei Xin, Hongyu Lin, Xianpei Han, Cao Liu, Jiansong Chen, Fan Yang, Guanglu Wan, Le Sun
2023 J jnl
CPPF: A contextual and post-processing-free model for automatic speech recognition.
CoRR
Lei Zhang, Zhengkun Tian, Xiang Chen, Jiaming Sun, Hongyu Xiang, Ke Ding, Guanglu Wan
2023 Misc conf
Covariance Regularization for Probabilistic Linear Discriminant Analysis.
ICASSP
Zhiyuan Peng, Mingjie Shao, Xuanji He, Xu Li, Tan Lee, Ke Ding, Guanglu Wan
2023 A* conf
Dialog-to-Actions: Building Task-Oriented Dialogue System via Action-Level Generation.
SIGIR
Yuncheng Hua, Xiangyu Xi, Zheng Jiang, Guanwei Zhang, Chaobo Sun, Guanglu Wan, Wei Ye
2023 J jnl
Dialog-to-Actions: Building Task-Oriented Dialogue System via Action-Level Generation.
CoRR
Yuncheng Hua, Xiangyu Xi, Zheng Jiang, Guanwei Zhang, Chaobo Sun, Guanglu Wan, Wei Ye
2023 — conf
ECOD: A Multi-modal Dataset for Intelligent Adjudication of E-Commerce Order Disputes.
NLPCC (1)
Liyi Chen, Shuaipeng Liu, Hailei Yan, Jie Liu, Lijie Wen, Guanglu Wan
2023 J jnl
Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter.
CoRR
Song Li, Yongbin You, Xuezhi Wang, Ke Ding, Guanglu Wan
2023 — conf
Exploiting Pseudo Future Contexts for Emotion Recognition in Conversations.
ADMA (1)
Yinyi Wei, Shuaipeng Liu, Hailei Yan, Wei Ye, Tong Mo, Guanglu Wan
2023 J jnl
Exploiting Pseudo Future Contexts for Emotion Recognition in Conversations.
CoRR
Yinyi Wei, Shuaipeng Liu, Hailei Yan, Wei Ye, Tong Mo, Guanglu Wan
2023 Misc conf
Peak-First CTC: Reducing the Peak Latency of CTC Models by Applying Peak-First Regularization.
ICASSP
Zhengkun Tian, Hongyu Xiang, Min Li, Feifei Lin, Ke Ding, Guanglu Wan
2023 A conf
Segment Augmentation and Prediction Consistency Neural Network for Multi-label Unknown Intent Detection.
CIKM
Miaoxin Chen, Cao Liu, Boqi Dai, Hai-Tao Zheng, Ting Song, Jiansong Chen, Guanglu Wan, Rui Xie
2022 A* conf
A Low-Cost, Controllable and Interpretable Task-Oriented Chatbot: With Real-World After-Sale Services as Example.
SIGIR
Xiangyu Xi, Chenxu Lv, Yuncheng Hua, Wei Ye, Chaobo Sun, Shuaipeng Liu, Fan Yang, Guanglu Wan
2022 J jnl
A Low-Cost, Controllable and Interpretable Task-Oriented Chatbot: With Real-World After-Sale Services as Example.
CoRR
Xiangyu Xi, Chenxu Lv, Yuncheng Hua, Wei Ye, Chaobo Sun, Shuaipeng Liu, Fan Yang, Guanglu Wan
2022 A conf
An Empirical Study of Language Model Integration for Transducer based Speech Recognition.
INTERSPEECH
Huahuan Zheng, Keyu An, Zhijian Ou, Chen Huang, Ke Ding, Guanglu Wan
2022 J jnl
An Empirical Study of Language Model Integration for Transducer based Speech Recognition.
CoRR
Huahuan Zheng, Keyu An, Zhijian Ou, Chen Huang, Ke Ding, Guanglu Wan
2022 A conf
CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASR.
INTERSPEECH
Keyu An, Huahuan Zheng, Zhijian Ou, Hongyu Xiang, Ke Ding, Guanglu Wan
2022 J jnl
CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASR.
CoRR
Keyu An, Huahuan Zheng, Zhijian Ou, Hongyu Xiang, Ke Ding, Guanglu Wan
2022 A* conf
Confidence Calibration for Intent Detection via Hyperspherical Space and Rebalanced Accuracy-Uncertainty Loss.
AAAI
Yantao Gong, Cao Liu, Fan Yang, Xunliang Cai, Guanglu Wan, Jiansong Chen, Weipeng Zhang, Houfeng Wang
2022 J jnl
Confidence Calibration for Intent Detection via Hyperspherical Space and Rebalanced Accuracy-Uncertainty Loss.
CoRR
Yantao Gong, Cao Liu, Fan Yang, Xunliang Cai, Guanglu Wan, Jiansong Chen, Weipeng Zhang, Houfeng Wang
2022 J jnl
Covariance Regularization for Probabilistic Linear Discriminant Analysis.
CoRR
Zhiyuan Peng, Mingjie Shao, Xuanji He, Xu Li, Tan Lee, Ke Ding, Guanglu Wan
2022 B conf
DESED: Dialogue-based Explanation for Sentence-level Event Detection.
COLING
Yinyi Wei, Shuaipeng Liu, Jianwei Lv, Xiangyu Xi, Hailei Yan, Wei Ye, Tong Mo, Fan Yang, Guanglu Wan
2022 A* conf
Dialogue Topic Segmentation via Parallel Extraction Network with Neighbor Smoothing.
SIGIR
Jinxiong Xia, Cao Liu, Jiansong Chen, Yuchen Li, Fan Yang, Xunliang Cai, Guanglu Wan, Houfeng Wang
2022 — conf
Label-free Knowledge Distillation with Contrastive Loss for Light-weight Speaker Recognition.
ISCSLP
Zhiyuan Peng, Xuanji He, Ke Ding, Tan Lee, Guanglu Wan
2022 J jnl
Label-free Knowledge Distillation with Contrastive Loss for Light-weight Speaker Recognition.
CoRR
Zhiyuan Peng, Xuanji He, Ke Ding, Tan Lee, Guanglu Wan
2022 — conf
MT-Speech at SemEval-2022 Task 10: Incorporating Data Augmentation and Auxiliary Task with Cross-Lingual Pretrained Language Model for Structured Sentiment Analysis.
SemEval@NAACL
Cong Chen, Jiansong Chen, Cao Liu, Fan Yang, Guanglu Wan, Jinxiong Xia
2022 A* conf
MUSIED: A Benchmark for Event Detection from Multi-Source Heterogeneous Informal Texts.
EMNLP
Xiangyu Xi, Jianwei Lv, Shuaipeng Liu, Wei Ye, Fan Yang, Guanglu Wan
2022 J jnl
MUSIED: A Benchmark for Event Detection from Multi-Source Heterogeneous Informal Texts.
CoRR
Xiangyu Xi, Jianwei Lv, Shuaipeng Liu, Wei Ye, Fan Yang, Guanglu Wan
2022 — conf
Multi-speaker Multi-style Text-to-speech Synthesis with Single-speaker Single-style Training Data Scenarios.
ISCSLP
Qicong Xie, Tao Li, Xinsheng Wang, Zhichao Wang, Lei Xie, Guoqiao Yu, Guanglu Wan
2022 J jnl
Peak-First CTC: Reducing the Peak Latency of CTC Models by Applying Peak-First Regularization.
CoRR
Zhengkun Tian, Hongyu Xiang, Min Li, Feifei Lin, Ke Ding, Guanglu Wan
2022 A conf
Unifying Cosine and PLDA Back-ends for Speaker Verification.
INTERSPEECH
Zhiyuan Peng, Xuanji He, Ke Ding, Tan Lee, Guanglu Wan
2022 J jnl
Unifying Cosine and PLDA Back-ends for Speaker Verification.
CoRR
Zhiyuan Peng, Xuanji He, Ke Ding, Tan Lee, Guanglu Wan
2021 A conf
Density-Based Dynamic Curriculum Learning for Intent Detection.
CIKM
Yantao Gong, Cao Liu, Jiazhen Yuan, Fan Yang, Xunliang Cai, Guanglu Wan, Jiansong Chen, Ruiyao Niu, Houfeng Wang
2021 J jnl
Density-Based Dynamic Curriculum Learning for Intent Detection.
CoRR
Yantao Gong, Cao Liu, Jiazhen Yuan, Fan Yang, Xunliang Cai, Guanglu Wan, Jiansong Chen, Ruiyao Niu, Houfeng Wang
2021 A* conf
Distant Supervision based Machine Reading Comprehension for Extractive Summarization in Customer Service.
SIGIR
Bing Ma, Cao Liu, Jingyu Wang, Shujie Hu, Fan Yang, Xunliang Cai, Guanglu Wan, Jiansong Chen, Jianxin Liao
2021 J jnl
Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios.
CoRR
Qicong Xie, Tao Li, Xinsheng Wang, Zhichao Wang, Lei Xie, Guoqiao Yu, Guanglu Wan
2020 A conf
Data Efficient Voice Cloning from Noisy Samples with Domain Adversarial Training.
INTERSPEECH
Jian Cong, Shan Yang, Lei Xie, Guoqiao Yu, Guanglu Wan
2020 J jnl
Data Efficient Voice Cloning from Noisy Samples with Domain Adversarial Training.
CoRR
Jian Cong, Shan Yang, Lei Xie, Guoqiao Yu, Guanglu Wan
2020 J jnl
Learning Speaker Embedding with Momentum Contrast.
CoRR
Ke Ding, Xuanji He, Guanglu Wan