Publications

Complete list of Yanjun Chen's papers: peer-reviewed publications, preprints, and works in submission on training environments, reward models, credit assignment, and reinforcement learning.

Peer-reviewed

2026

  1. NeurIPS
    FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control
    Jun Xue, Junze Wang, Shanze Wang, and
    In Advances in Neural Information Processing Systems (NeurIPS), 2026
  2. EMNLP Findings
    Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
    Xinghao Chen, Anhao Zhao, Heming Xia, and
    In Findings of the Association for Computational Linguistics: EMNLP 2026, 2026
  3. IEEE TVT
    Breaking the Pre-Planning Barrier: Adaptive Real-Time Coordination of Heterogeneous UAVs
    Yuhan Hu, Yirong Sun, Yanjun Chen, and
    IEEE Transactions on Vehicular Technology, 2026
  4. Measurement
    Auditable progressive multimodal bearing fault diagnosis with Large language model Screening
    Jinghan Wang, Gaoliang Peng, Yanjun Chen, and
    Measurement, 2026

2025

  1. EMNLP
    PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks
    Yunuo Liu, Dawei Zhu, Zena Al-Khalili, and
    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
  2. ACL Findings
    Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning
    Xinghao Chen, Zhijing Sun, Wenjin Guo, and
    In Findings of the Association for Computational Linguistics: ACL 2025, 2025
  3. NAACL SRW
    Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation
    Yirong Sun, Dawei Zhu, Yanjun Chen, and
    In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), 2025

2024

  1. EMNLP
    The Accuracy Paradox in RLHF: When Better Reward Models Don’t Yield Better Language Models
    Yanjun Chen, Dawei Zhu, Yirong Sun, and
    In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024

Preprints & under review

2026

  1. arXiv
    Action Shaping: Policies Absorb What They Can Express
    Yanjun Chen, Jinghan Wang, Xiaoyu Shen, and
    arXiv preprint arXiv:2609.32752, 2026
    In submission.
  2. arXiv
    The Trace Is the State: Exact Credit Assignment for LLM Agent Teams
    Yanjun Chen, Yirong Sun, Hanlin Wang, and
    arXiv preprint arXiv:2603.06859, 2026
    In submission.
  3. arXiv
    SonicBench: Dissecting the Physical Perception Bottleneck in Large Audio Language Models
    Yirong Sun, Yanjun Chen, Xin Qiu, and
    arXiv preprint arXiv:2601.11039, 2026
  4. arXiv
    Digital Twin-Driven Adaptive Sim-to-Real Alignment via Reinforcement Learning for Vibration-Based Bearing Health Monitoring Under Data Scarcity
    Jinghan Wang, Yanjun Chen, Wei Zhang, and
    arXiv preprint arXiv:2606.24954, 2026
  5. arXiv
    Cascaded Multi-Granularity Pruning for On-Device LLM Inference in Industrial IoT
    Jinghan Wang, Yanjun Chen, Wei Zhang, and
    arXiv preprint arXiv:2606.26861, 2026

2025

  1. arXiv
    Integrating Chain-of-Thought for Multimodal Alignment: A Study on 3D Vision-Language Learning
    Yanjun Chen, Yirong Sun, Xinghao Chen, and
    arXiv preprint arXiv:2503.06232, 2025
  2. arXiv
    LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model
    Yirong Sun, Yizhong Geng, Peidong Wei, and
    arXiv preprint arXiv:2508.15418, 2025
  3. arXiv
    MA-ROESL: Motion-aware Rapid Reward Optimization for Efficient Robot Skill Learning from Single Videos
    Xianghui Wang, Xinming Zhang, Yanjun Chen, and
    arXiv preprint arXiv:2505.08367, 2025

2024

  1. arXiv
    Rethinking Soft Actor-Critic in High-Dimensional Action Spaces: The Cost of Ignoring Distribution Shift
    Yanjun Chen, Xinming Zhang, Xianghui Wang, and
    arXiv preprint arXiv:2410.16739, 2024