Dong Yu

Venues

Frequent coauthors

Papers

1. Audio-Thinker: Guiding Large Audio Language Model When and How to Think via Reinforcement Learning
   AAAI 2026 ·

   Shu Wu

   DBLP profile ↗ORCID search ↗
2. Crossing the Reward Bridge: Expanding Reinforcement Learning with Verifiable Rewards Across Diverse Domains
   ACL 2026 ·

   Yi Su

   DBLP profile ↗ORCID search ↗
3. DegVoC: Revisiting Neural Vocoder from a Degradation Perspective
   AAAI 2026 ·

   Andong Li

   DBLP profile ↗ORCID search ↗
4. EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving
   ACL 2026 ·

   Mukai Li

   DBLP profile ↗ORCID search ↗
5. Enhancing Stability and Fidelity for Zero-Shot TTS with a Multi-Level Evaluator
   AAAI 2026 ·

   Hualei Wang

   DBLP profile ↗ORCID search ↗
6. Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification
   ACL 2026 ·

   Yuxuan Wan

   DBLP profile ↗ORCID search ↗
7. Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation
   ACL 2026 ·

   Wei-Cheng Tseng

   DBLP profile ↗ORCID search ↗
8. Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning
   ACL 2026 ·

   Haolin Liu

   DBLP profile ↗ORCID search ↗
9. Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data
   ACL 2026 ·

   Zhenwen Liang

   DBLP profile ↗ORCID search ↗
10. UniCUE: Unified Recognition and Generation Framework for Chinese Cued Speech Video-to-Speech Generation
    AAAI 2026 ·

    Jinting Wang

    DBLP profile ↗ORCID search ↗
11. VCB Bench: An Evaluation Benchmark for Audio-Grounded Large Language Model Conversational Agents
    ACL 2026 ·

    Jiliang Hu

    DBLP profile ↗ORCID search ↗
12. Verified Critical Step Optimization for LLM Agents
    ACL 2026 ·

    Mukai Li

    DBLP profile ↗ORCID search ↗
13. WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models
    ACL 2026 ·

    Rui Wang

    DBLP profile ↗ORCID search ↗
14. WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms
    EACL 2026 ·

    Zhisong Zhang

    DBLP profile ↗ORCID search ↗
15. Your Reasoning Model is Secretly a Reward Model - Optimization-Free Verification from Experience
    ACL 2026 ·

    Zhenwen Liang

    DBLP profile ↗ORCID search ↗
16. A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression
    ACL 2025 ·

    Chenlong Deng

    DBLP profile ↗ORCID search ↗
17. Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models
    ACL 2025 ·

    Zhisong Zhang

    DBLP profile ↗ORCID search ↗
18. BridgeVoC: Neural Vocoder with Schrödinger Bridge
    IJCAI 2025 ·

    Tong Lei

    DBLP profile ↗ORCID search ↗
19. Cognitive Kernel: An Open-source Agent System towards Generalist Autopilots
    NAACL 2025 ·

    Hongming Zhang

    DBLP profile ↗ORCID search ↗
20. DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search
    ICLR 2025 ·

    Murong Yue

    DBLP profile ↗ORCID search ↗
21. DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?
    ICLR 2025 ·

    Liqiang Jing

    DBLP profile ↗ORCID search ↗
22. DeFine: Decision-Making with Analogical Reasoning over Factor Profiles
    ACL 2025 ·

    Yebowen Hu

    DBLP profile ↗ORCID search ↗
23. DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse Scenes
    EMNLP 2025 ·

    Zhaowei Wang

    DBLP profile ↗ORCID search ↗
24. Do NOT Think That Much for 2+3=? On the Overthinking of Long Reasoning Models
    ICML 2025 ·

    Xingyu Chen

    DBLP profile ↗ORCID search ↗
25. Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls
    ACL 2025 ·

    Ante Wang

    DBLP profile ↗ORCID search ↗
26. Efficient Multilingual ASR Finetuning via LoRA Language Experts
    InterSpeech 2025 ·

    Jiahong Li

    DBLP profile ↗ORCID search ↗
27. EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer
    InterSpeech 2025 ·

    Jiarui Hai

    DBLP profile ↗ORCID search ↗
28. From Continuous to Discrete: Cross-Domain Collaborative General Speech Enhancement via Hierarchical Language Models
    ACM MM 2025 ·

    Zhaoxi Mu

    DBLP profile ↗ORCID search ↗
29. Hearing from Silence: Reasoning Audio Descriptions from Silent Videos via Vision-Language Model
    InterSpeech 2025 ·

    Yong Ren

    DBLP profile ↗ORCID search ↗
30. Improving LLM General Preference Alignment via Optimistic Online Mirror Descent
    NeurIPS 2025 ·

    Yuheng Zhang

    DBLP profile ↗ORCID search ↗
31. Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
    ICLR 2025 ·

    Yuheng Zhang

    DBLP profile ↗ORCID search ↗
32. LeVo: High-Quality Song Generation with Multi-Preference Alignment
    NeurIPS 2025 ·

    Shun Lei

    DBLP profile ↗ORCID search ↗
33. LiteSearch: Efficient Tree Search with Dynamic Exploration Budget for Math Reasoning
    AAAI 2025 ·

    Ante Wang

    DBLP profile ↗ORCID search ↗
34. LoGU: Long-form Generation with Uncertainty Expressions
    ACL 2025 ·

    Ruihan Yang

    DBLP profile ↗ORCID search ↗
35. LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
    ICLR 2025 ·

    Di Wu

    DBLP profile ↗ORCID search ↗
36. Low-Bit Quantization Favors Undertrained LLMs
    ACL 2025 ·

    Xu Ouyang

    DBLP profile ↗ORCID search ↗
37. MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data Curation
    NeurIPS 2025 ·

    Zhenwen Liang

    DBLP profile ↗ORCID search ↗
38. Mitigating Audiovisual Mismatch in Visual-Guide Audio Captioning
    InterSpeech 2025 ·

    Le Xu

    DBLP profile ↗ORCID search ↗
39. OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization
    ACL 2025 ·

    Hongliang He

    DBLP profile ↗ORCID search ↗
40. Recall with Reasoning: Chain-of-Thought Distillation for Mamba's Long-Context Memory and Extrapolation
    EMNLP 2025 ·

    Jun-Yu Ma

    DBLP profile ↗ORCID search ↗
41. RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph
    ICLR 2025 ·

    Siru Ouyang

    DBLP profile ↗ORCID search ↗
42. Retrieval-augmented GUI Agents with Generative Guidelines
    EMNLP 2025 ·

    Ran Xu

    DBLP profile ↗ORCID search ↗
43. Router-Tuning: A Simple and Effective Approach for Dynamic Depth
    EMNLP 2025 ·

    Shwai He

    DBLP profile ↗ORCID search ↗
44. Scaling beyond Denoising: Submitted System and Findings in URGENT Challenge 2025
    InterSpeech 2025 ·

    Zhihang Sun

    DBLP profile ↗ORCID search ↗
45. The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
    NeurIPS 2025 ·

    Ke Ji

    DBLP profile ↗ORCID search ↗
46. Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models
    NeurIPS 2025 ·

    Yue Wang

    DBLP profile ↗ORCID search ↗
47. Towards Diverse and Efficient Audio Captioning via Diffusion Models
    InterSpeech 2025 ·

    Manjie Xu

    DBLP profile ↗ORCID search ↗
48. Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards
    NeurIPS 2025 ·

    Xiaoyuan Liu

    DBLP profile ↗ORCID search ↗
49. Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
    NeurIPS 2025 ·

    Mengru Wang

    DBLP profile ↗ORCID search ↗
50. UNCLE: Benchmarking Uncertainty Expressions in Long-Form Generation
    EMNLP 2025 ·

    Ruihan Yang

    DBLP profile ↗ORCID search ↗
51. UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
    NeurIPS 2025 ·

    Chenlong Deng

    DBLP profile ↗ORCID search ↗
52. Video-to-Audio Generation with Fine-grained Temporal Semantics
    InterSpeech 2025 ·

    Yuchen Hu

    DBLP profile ↗ORCID search ↗
53. VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining
    InterSpeech 2025 ·

    Jianheng Zhuo

    DBLP profile ↗ORCID search ↗
54. WAKE: Watermarking Audio with Key Enrichment
    InterSpeech 2025 ·

    Yaoxun Xu

    DBLP profile ↗ORCID search ↗
55. WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback
    EMNLP 2025 ·

    Minda Hu

    DBLP profile ↗ORCID search ↗
56. WebEvolver: Enhancing Web Agent Self-Improvement with Co-evolving World Model
    EMNLP 2025 ·

    Tianqing Fang

    DBLP profile ↗ORCID search ↗
57. A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning
    NAACL 2024 ·

    Ruixin Hong

    DBLP profile ↗ORCID search ↗
58. Abstraction-of-Thought Makes Language Models Better Reasoners
    EMNLP 2024 ·

    Ruixin Hong

    DBLP profile ↗ORCID search ↗
59. CLOMO: Counterfactual Logical Modification with Large Language Models
    ACL 2024 ·

    Yinya Huang

    DBLP profile ↗ORCID search ↗
60. Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models
    EMNLP 2024 ·

    Wenhao Yu

    DBLP profile ↗ORCID search ↗
61. Comparing Discrete and Continuous Space LLMs for Speech Recognition
    InterSpeech 2024 ·

    Yaoxun Xu

    DBLP profile ↗ORCID search ↗
62. Dense X Retrieval: What Retrieval Granularity Should We Use?
    EMNLP 2024 ·

    Tong Chen

    DBLP profile ↗ORCID search ↗
63. Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models
    ACL 2024 ·

    Xinran Zhao

    DBLP profile ↗ORCID search ↗
64. From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
    NAACL 2024 ·

    Xuansheng Wu

    DBLP profile ↗ORCID search ↗
65. Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer
    ACL 2024 ·

    Yongxin Zhu

    DBLP profile ↗ORCID search ↗
66. Improving LLM Generations via Fine-Grained Self-Endorsement
    ACL 2024 ·

    Ante Wang

    DBLP profile ↗ORCID search ↗
67. InFoBench: Evaluating Instruction Following Ability in Large Language Models
    ACL 2024 ·

    Yiwei Qin

    DBLP profile ↗ORCID search ↗
68. Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning
    EMNLP 2024 ·

    Zhihan Zhang

    DBLP profile ↗ORCID search ↗
69. MM-LLMs: Recent Advances in MultiModal Large Language Models
    ACL 2024 ·

    Duzhen Zhang

    DBLP profile ↗ORCID search ↗
70. MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning
    NAACL 2024 ·

    Fuxiao Liu

    DBLP profile ↗ORCID search ↗
71. Make-A-Voice: Revisiting Voice Large Language Models as Scalable Multilingual and Multitask Learners
    ACL 2024 ·

    Rongjie Huang

    DBLP profile ↗ORCID search ↗
72. Multi-Channel Multi-Speaker ASR Using Target Speaker's Solo Segment
    InterSpeech 2024 ·

    Yiwen Shao

    DBLP profile ↗ORCID search ↗
73. Polarity Calibration for Opinion Summarization
    NAACL 2024 ·

    Yuanyuan Lei

    DBLP profile ↗ORCID search ↗
74. Prompt-guided Precise Audio Editing with Diffusion Models
    ICML 2024 ·

    Manjie Xu

    DBLP profile ↗ORCID search ↗
75. RIR-SF: Room Impulse Response Based Spatial Feature for Target Speech Recognition in Multi-Channel Multi-Speaker Scenarios
    InterSpeech 2024 ·

    Yiwen Shao

    DBLP profile ↗ORCID search ↗
76. Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment
    ICML 2024 ·

    Rui Yang

    DBLP profile ↗ORCID search ↗
77. Self-Consistency Boosts Calibration for Math Reasoning
    EMNLP 2024 ·

    Ante Wang

    DBLP profile ↗ORCID search ↗
78. Skills-in-Context: Unlocking Compositionality in Large Language Models
    EMNLP 2024 ·

    Jiaao Chen

    DBLP profile ↗ORCID search ↗
79. SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMs
    ACL 2024 ·

    Yebowen Hu

    DBLP profile ↗ORCID search ↗
80. Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations
    NAACL 2024 ·

    Sihao Chen

    DBLP profile ↗ORCID search ↗
81. The Trickle-down Impact of Reward Inconsistency on RLHF
    ICLR 2024 ·

    Lingfeng Shen

    DBLP profile ↗ORCID search ↗
82. Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
    NeurIPS 2024 ·

    Ye Tian

    DBLP profile ↗ORCID search ↗
83. WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models
    ACL 2024 ·

    Hongliang He

    DBLP profile ↗ORCID search ↗
84. When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives
    EMNLP 2024 ·

    Yebowen Hu

    DBLP profile ↗ORCID search ↗