GW
Guanglu Wan
cs.CLeess.AScs.SDcs.AIcs.CVcs.LGcs.MMcs.DCcs.HC
On Valency
published · living versionsW_tehuxtkr·v1 · currentpublished
Meituan-Robotics-0: A Vision-Language-Action Foundation Model for Desktop Manipulation
with Meituan Robotics Team, Caicheng Wang, Chen Zhao, Chengpeng Jin +33
1 version
Preprints & journals
35 papers in the corpus · 2020–2026RAP: A Dataset for Paper-to-Poster Generation via Declarative Markup from Human-Crafted Exemplars2610.23230v1 · Haonan Han, Yukang Lin, Minliang Lin et al.2026 · 0 citationsarXiv
ReasonUni: Reasoning-Augmented Reconstruction Advances Unified Multimodal Models2610.20781v1 · Feize Wu, Zhiyuan Yan, Yuhuan Hong et al.2026 · 0 citationsarXiv
PRISM-Bench: An Audio-Centric Diagnostic Benchmark for Text-to-Audio-Video Generation2609.04867v2 · Yuchen Sun, Qian Yang, Jun Wang et al.2026 · 0 citationsarXiv
UniSpace: Unified Visual Representation and Scalable Multimodal Modeling2608.08676v1 · Jinbo Yan, Limeng Qiao, Jie Qin et al.2026 · 0 citationsarXiv
MT-Web2Code: Benchmarking Coding Agents on Multi-Turn Regional Reconstruction and Localized Modification2608.03474v1 · Qiming Li, Shujie Hu, Haohan Liu et al.2026 · 0 citationsarXiv
HoloCount: A Holistic Visual Counting Benchmark for MLLMs2607.06420v1 · Jinhong Deng, Limeng Qiao, Guanglu Wan2026 · 0 citationsarXiv
X2SAM: Any Segmentation in Images and Videos2605.00891v1 · Hao Wang, Limeng Qiao, Chi Zhang et al.2026 · 0 citationsarXiv
GeoAlign: Geometric Feature Realignment for MLLM Spatial Reasoning2604.12630v1 · Zhaochen Liu, Limeng Qiao, Guanglu Wan et al.2026 · 0 citationsarXiv
LongCat-AudioDiT: High-Fidelity Diffusion Text-to-Speech in the Waveform Latent Space2603.29339v1 · Detai Xin, Shujie Hu, Chengzuo Yang et al.2026 · 0 citationsarXiv
Omni-AutoThink: Adaptive Multimodal Reasoning via Reinforcement Learning2512.03783v2 · Dongchao Yang, Songxiang Liu, Disong Wang et al.2025 · 0 citationsarXiv
LongCat-Flash-Omni Technical Report2511.00279v2 · Meituan LongCat Team, Bairui Wang, Bayan et al.2025 · 0 citationsarXiv
LongCat-Audio-Codec: An Audio Tokenizer and Detokenizer Solution Designed for Speech Large Language Models2510.15227v1 · Xiaohan Zhao, Hongyu Xiang, Shengze Ye et al.2025 · 0 citationsarXiv
Audio Turing Test: Benchmarking the Human-likeness of Large Language Model-based Text-to-Speech Systems in Chinese2505.11200v1 · Xihuai Wang, Ziyi Zhao, Siyu Ren et al.2025 · 0 citationsarXiv
AS-Speech: Adaptive Style For Speech Synthesis2409.05730v1 · Zhipeng Li, Xiaofen Xing, Jun Wang et al.2024 · 0 citationsarXiv
MSR-86K: An Evolving, Multilingual Corpus with 86,300 Hours of Transcribed Audio for Speech Recognition Research2406.18301v1 · Song Li, Yongbin You, Xuezhi Wang et al.2024 · 3 citationsarXiv
CLAQ: Pushing the Limits of Low-Bit Post-Training Quantization for LLMs2405.17233v2 · Haoyu Wang, Bei Liu, Hang Shao et al.2024 · 2 citationsarXiv
Learning or Self-aligning? Rethinking Instruction Fine-tuning2402.18243v3 · Mengjie Ren, Boxi Cao, Hongyu Lin et al.2024 · 9 citationsarXiv
A Task-oriented Dialog Model with Task-progressive and Policy-aware Pre-training2310.00597v1 · Lucen Zhong, Hengtong Lu, Caixia Yuan et al.2023 · 0 citationsarXiv
Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter2309.09443v2 · Song Li, Yongbin You, Xuezhi Wang et al.2023 · 6 citationsarXiv
CPPF: A contextual and post-processing-free model for automatic speech recognition2309.07413v2 · Lei Zhang, Zhengkun Tian, Xiang Chen et al.2023 · 0 citationsarXiv
Exploiting Pseudo Future Contexts for Emotion Recognition in Conversations2306.15376v1 · Yinyi Wei, Shuaipeng Liu, Hailei Yan et al.2023 · 5 citationsarXiv
Dialog-to-Actions: Building Task-Oriented Dialogue System via Action-Level Generation2304.00884v1 · Yuncheng Hua, Xiangyu Xi, Zheng Jiang et al.2023 · 2 citationsarXiv
Covariance Regularization for Probabilistic Linear Discriminant Analysis2212.03039v1 · Zhiyuan Peng, Mingjie Shao, Xuanji He et al.2022 · 1 citationarXiv
Label-free Knowledge Distillation with Contrastive Loss for Light-weight Speaker Recognition2212.03090v1 · Zhiyuan Peng, Xuanji He, Ke Ding et al.2022 · 9 citationsarXiv
MUSIED: A Benchmark for Event Detection from Multi-Source Heterogeneous Informal Texts2211.13896v1 · Xiangyu Xi, Jianwei Lv, Shuaipeng Liu et al.2022 · 3 citationsarXiv
Peak-First CTC: Reducing the Peak Latency of CTC Models by Applying Peak-First Regularization2211.03284v2 · Zhengkun Tian, Hongyu Xiang, Min Li et al.2022 · 4 citationsarXiv
A Low-Cost, Controllable and Interpretable Task-Oriented Chatbot: With Real-World After-Sale Services as Example2205.06436v1 · Xiangyu Xi, Chenxu Lv, Yuncheng Hua et al.2022 · 0 citationsarXiv
Unifying Cosine and PLDA Back-ends for Speaker Verification2204.10523v1 · Zhiyuan Peng, Xuanji He, Ke Ding et al.2022 · 9 citationsarXiv
CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASR2203.16758v2 · Keyu An, Huahuan Zheng, Zhijian Ou et al.2022 · 14 citationsarXiv
An Empirical Study of Language Model Integration for Transducer based Speech Recognition2203.16776v4 · Huahuan Zheng, Keyu An, Zhijian Ou et al.2022 · 5 citationsarXiv
Confidence Calibration for Intent Detection via Hyperspherical Space and Rebalanced Accuracy-Uncertainty Loss2203.09278v1 · Yantao Gong, Cao Liu, Fan Yang et al.2022 · 5 citationsarXiv
Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios2112.12743v1 · Qicong Xie, Tao Li, Xinsheng Wang et al.2021 · 9 citationsarXiv
Density-Based Dynamic Curriculum Learning for Intent Detection2108.10674v1 · Yantao Gong, Cao Liu, Jiazhen Yuan et al.2021 · 14 citationsarXiv
Data Efficient Voice Cloning from Noisy Samples with Domain Adversarial Training2008.04265v2 · Jian Cong, Shan Yang, Lei Xie et al.2020 · 33 citationsarXiv
Learning Speaker Embedding with Momentum Contrast2001.01986v2 · Ke Ding, Xuanji He, Guanglu Wan2020 · 9 citationsarXiv
Career total: 45 works. 35 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.