QC

Qinyuan Cheng

cs.CLcs.AIcs.SDeess.AScs.CVcs.LGcs.HCcs.RO

On Valency

published · living versions

W_725xggce·v1 · currentpublished

GigaSpeech 3: Scaling Multi-Dialect Arabic Speech Recognition with Weakly Labeled Data

with Junzhe Liu, Yujie Tu, Yifan Yang, Peng Wang +11

1 version

Preprints & journals

31 papers in the corpus · 2022–2026

XTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary Decisions2610.04400v1 · Zhanxun Liu, Yifan Duan, Hengtao Wu et al.2026 · 0 citationsarXiv

MOSS-VL Technical Report2608.15045v1 · Pengyu Wang, Chenkun Tan, Shaojun Zhou et al.2026 · 0 citationsarXiv

OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation2607.23855v2 · Jun Zhan, Chen Yang, Yitian Gong et al.2026 · 0 citationsarXiv

X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning2605.05611v2 · Rixi Xu, Qingyu Liu, Haitao Li et al.2026 · 0 citationsarXiv

MOSS-VoiceGenerator: Create Realistic Voices with Natural Language Descriptions2603.28086v1 · Kexin Huang, Liwei Fan, Botian Jiang et al.2026 · 0 citationsarXiv

MOSS-TTSD: Text to Spoken Dialogue Generation2603.19739v1 · Yuqian Zhang, Donghua Yu, Zhengyuan Lin et al.2026 · 0 citationsarXiv

MOSS-TTS Technical Report2603.18090v2 · Yitian Gong, Botian Jiang, Yiwei Zhao et al.2026 · 0 citationsarXiv

AI Can Learn Scientific Taste2603.14473v3 · Jingqi Tong, Mingzhe Li, Hangcheng Li et al.2026 · 0 citationsarXiv

MOVA: Towards Scalable and Synchronized Video-Audio Generation2602.08794v2 · SII-OpenMOSS Team: Donghua Yu, Mingshu Chen, Qi Chen et al.2026 · 1 citationarXiv

WESR: Scaling and Evaluating Word-level Event-Speech Recognition2601.04508v1 · Chenchen Yang, Kexin Huang, Liwei Fan et al.2026 · 0 citationsarXiv

MOSS Transcribe Diarize Technical Report2601.01554v7 · MOSI.AI: Donghua Yu, Zhengyuan Lin, Hanfu Chen et al.2026 · 0 citationsarXiv

MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance2510.00499v2 · Xingjian Zhao, Zhe Xu, Qinyuan Cheng et al.2025 · 0 citationsarXiv

VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions2509.09716v2 · Jun Zhan, Mingyang Han, Yuxuan Xie et al.2025 · 0 citationsarXiv

CodecBench: A Comprehensive Benchmark for Acoustic and Semantic Evaluation2508.20660v1 · Ruifan Deng, Yitian Gong, Qinghui Gao et al.2025 · 0 citationsarXiv

XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs2506.23325v2 · Yitian Gong, Luozhijie Jin, Ruifan Deng et al.2025 · 0 citationsarXiv

R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning2505.23794v2 · Yuan Li, Qi Luo, Xiaonan Li et al.2025 · 4 citationsarXiv

World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning2503.10480v1 · Siyin Wang, Zhaoye Fei, Qinyuan Cheng et al.2025 · 5 citationsarXiv

How to Mitigate Overfitting in Weak-to-strong Generalization?2503.04249v1 · Junhao Shi, Qinyuan Cheng, Zhaoye Fei et al.2025 · 0 citationsarXiv

AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language Models2502.16906v1 · Qin Zhu, Fei Huang, Runyu Peng et al.2025 · 0 citationsarXiv

Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?2502.12215v2 · Zhiyuan Zeng, Qinyuan Cheng, Zhangyue Yin et al.2025 · 6 citationsarXiv

Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective2412.14135v1 · Zhiyuan Zeng, Qinyuan Cheng, Zhangyue Yin et al.2024 · 4 citationsarXiv

Case2Code: Scalable Synthetic Data for Code Generation2407.12504v2 · Yunfan Shao, Linyang Li, Yichuan Ma et al.2024 · 0 citationsarXiv

Scaling Laws for Fact Memorization of Large Language Models2406.15720v1 · Xingyu Lu, Xiaonan Li, Qinyuan Cheng et al.2024 · 8 citationsarXiv

Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model2406.15279v2 · Siyin Wang, Xingsong Ye, Qinyuan Cheng et al.2024 · 1 citationNAACL 2025

Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models2405.12939v1 · Zhangyue Yin, Qiushi Sun, Qipeng Guo et al.2024 · 2 citationsarXiv

Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT2402.12201v1 · Zhengfu He, Xuyang Ge, Qiong Tang et al.2024 · 2 citationsarXiv

Can AI Assistants Know What They Don't Know?2401.13275v2 · Qinyuan Cheng, Tianxiang Sun, Xiangyang Liu et al.2024 · 2 citationsarXiv

Evaluating Hallucinations in Chinese Large Language Models2310.03368v4 · Qinyuan Cheng, Tianxiang Sun, Wenwei Zhang et al.2023 · 9 citationsarXiv

Improving Contrastive Learning of Sentence Embeddings from AI Feedback2305.01918v3 · Qinyuan Cheng, Xiaogui Yang, Tianxiang Sun et al.2023 · 24 citationsarXiv

Mitigating Negative Style Transfer in Hybrid Dialogue System2212.07183v1 · Shimin Li, Qinyuan Cheng, Linyang Li et al.2022 · 2 citationsarXiv

Is MultiWOZ a Solved Task? An Interactive TOD Evaluation Framework with User Simulator2210.14529v1 · Qinyuan Cheng, Linyang Li, Guofeng Quan et al.2022 · 10 citationsarXiv

Career total: 41 works. 31 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.