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
- NeurIPSFastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid ControlIn Advances in Neural Information Processing Systems (NeurIPS), 2026
@inproceedings{xue2026fastdsac, title = {{FastDSAC}: Unlocking the Potential of Maximum Entropy {RL} in High-Dimensional Humanoid Control}, author = {Xue, Jun and Wang, Junze and Wang, Shanze and Zhang, Xinming and Chen, Yanjun and Zhang, Wei}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2026}, } - EMNLP FindingsReasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought ReasoningIn Findings of the Association for Computational Linguistics: EMNLP 2026, 2026
@inproceedings{chen2025reasoning, title = {Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning}, author = {Chen, Xinghao and Zhao, Anhao and Xia, Heming and Lu, Xuan and Wang, Hanlin and Chen, Yanjun and Zhang, Wei and Wang, Jian and Li, Wenjie and Shen, Xiaoyu}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2026}, year = {2026}, } - IEEE TVTBreaking the Pre-Planning Barrier: Adaptive Real-Time Coordination of Heterogeneous UAVsIEEE Transactions on Vehicular Technology, 2026
@article{hu2025uav, title = {Breaking the Pre-Planning Barrier: Adaptive Real-Time Coordination of Heterogeneous {UAVs}}, author = {Hu, Yuhan and Sun, Yirong and Chen, Yanjun and Chen, Xinghao and Shen, Xiaoyu and Zhang, Wei}, journal = {IEEE Transactions on Vehicular Technology}, year = {2026}, pages = {1--19}, doi = {10.1109/TVT.2026.3735334}, } - MeasurementAuditable progressive multimodal bearing fault diagnosis with Large language model ScreeningMeasurement, 2026
@article{wang2026auditable, title = {Auditable progressive multimodal bearing fault diagnosis with Large language model Screening}, author = {Wang, Jinghan and Peng, Gaoliang and Chen, Yanjun and Zhang, Wei and Wu, Wentao and Liu, Tianchen}, journal = {Measurement}, volume = {292}, pages = {123183}, year = {2026}, doi = {10.1016/j.measurement.2026.123183}, }
2025
- EMNLPPricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing TasksIn Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
@inproceedings{liu2025pricinglogic, title = {{PricingLogic}: Evaluating {LLMs} Reasoning on Complex Tourism Pricing Tasks}, author = {Liu, Yunuo and Zhu, Dawei and Al-Khalili, Zena and Cheng, Dai and Chen, Yanjun and Klakow, Dietrich and Zhang, Wei and Shen, Xiaoyu}, booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, year = {2025}, } - ACL FindingsUnveiling the Key Factors for Distilling Chain-of-Thought ReasoningIn Findings of the Association for Computational Linguistics: ACL 2025, 2025
@inproceedings{chen2025distilling, title = {Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning}, author = {Chen, Xinghao and Sun, Zhijing and Guo, Wenjin and Zhang, Miaoran and Chen, Yanjun and Sun, Yirong and Su, Hui and Pan, Yijie and Klakow, Dietrich and Li, Wenjie and Shen, Xiaoyu}, booktitle = {Findings of the Association for Computational Linguistics: ACL 2025}, year = {2025}, } - NAACL SRWFine-Grained and Multi-Dimensional Metrics for Document-Level Machine TranslationIn 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
@inproceedings{sun2025finegrained, title = {Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation}, author = {Sun, Yirong and Zhu, Dawei and Chen, Yanjun and Xiao, Erjia and Chen, Xinghao and Shen, Xiaoyu}, booktitle = {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)}, year = {2025}, }
2024
- EMNLPThe Accuracy Paradox in RLHF: When Better Reward Models Don’t Yield Better Language ModelsIn Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024
@inproceedings{chen2024accuracy, title = {The Accuracy Paradox in {RLHF}: When Better Reward Models Don't Yield Better Language Models}, author = {Chen, Yanjun and Zhu, Dawei and Sun, Yirong and Chen, Xinghao and Zhang, Wei and Shen, Xiaoyu}, booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, year = {2024}, }
Preprints & under review
2026
- arXivAction Shaping: Policies Absorb What They Can ExpressarXiv preprint arXiv:2609.32752, 2026In submission.
@article{chen2026action, title = {Action Shaping: Policies Absorb What They Can Express}, author = {Chen, Yanjun and Wang, Jinghan and Shen, Xiaoyu and Li, Wenjie and Zhang, Wei}, journal = {arXiv preprint arXiv:2609.32752}, year = {2026}, note = {In submission.} } - arXivThe Trace Is the State: Exact Credit Assignment for LLM Agent TeamsarXiv preprint arXiv:2603.06859, 2026In submission.
@article{chen2026exact, title = {The Trace Is the State: Exact Credit Assignment for {LLM} Agent Teams}, author = {Chen, Yanjun and Sun, Yirong and Wang, Hanlin and Wang, Jinghan and Zhang, Xinming and Shen, Xiaoyu and Li, Wenjie and Zhang, Wei}, journal = {arXiv preprint arXiv:2603.06859}, year = {2026}, note = {In submission.} } - arXivSonicBench: Dissecting the Physical Perception Bottleneck in Large Audio Language ModelsarXiv preprint arXiv:2601.11039, 2026
@article{sun2026sonicbench, title = {{SonicBench}: Dissecting the Physical Perception Bottleneck in Large Audio Language Models}, author = {Sun, Yirong and Chen, Yanjun and Qiu, Xin and Zhang, Gang and Chen, Hongyu and Wu, Daokuan and Li, Chengming and Yang, Min and Zhu, Dawei and Zhang, Wei and Shen, Xiaoyu}, journal = {arXiv preprint arXiv:2601.11039}, year = {2026}, } - arXivDigital Twin-Driven Adaptive Sim-to-Real Alignment via Reinforcement Learning for Vibration-Based Bearing Health Monitoring Under Data ScarcityarXiv preprint arXiv:2606.24954, 2026
@article{wang2026digitaltwin, title = {Digital Twin-Driven Adaptive Sim-to-Real Alignment via Reinforcement Learning for Vibration-Based Bearing Health Monitoring Under Data Scarcity}, author = {Wang, Jinghan and Chen, Yanjun and Zhang, Wei and Wu, Wentao and Liu, Tianchen and Peng, Gaoliang}, journal = {arXiv preprint arXiv:2606.24954}, year = {2026}, } - arXivCascaded Multi-Granularity Pruning for On-Device LLM Inference in Industrial IoTarXiv preprint arXiv:2606.26861, 2026
@article{wang2026cascaded, title = {Cascaded Multi-Granularity Pruning for On-Device {LLM} Inference in Industrial {IoT}}, author = {Wang, Jinghan and Chen, Yanjun and Zhang, Wei and Huang, Xiaotong and Liu, Tianchen and Peng, Gaoliang}, journal = {arXiv preprint arXiv:2606.26861}, year = {2026}, }
2025
- arXivIntegrating Chain-of-Thought for Multimodal Alignment: A Study on 3D Vision-Language LearningarXiv preprint arXiv:2503.06232, 2025
@article{chen2025multimodal3d, title = {Integrating Chain-of-Thought for Multimodal Alignment: A Study on {3D} Vision-Language Learning}, author = {Chen, Yanjun and Sun, Yirong and Chen, Xinghao and Wang, Jian and Shen, Xiaoyu and Li, Wenjie and Zhang, Wei}, journal = {arXiv preprint arXiv:2503.06232}, year = {2025}, } - arXivLLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech ModelarXiv preprint arXiv:2508.15418, 2025
@article{sun2025llaso, title = {{LLaSO}: A Foundational Framework for Reproducible Research in Large Language and Speech Model}, author = {Sun, Yirong and Geng, Yizhong and Wei, Peidong and Chen, Yanjun and Yang, Jinghan and Chen, Rongfei and Zhang, Wei and Shen, Xiaoyu}, journal = {arXiv preprint arXiv:2508.15418}, year = {2025}, } - arXivMA-ROESL: Motion-aware Rapid Reward Optimization for Efficient Robot Skill Learning from Single VideosarXiv preprint arXiv:2505.08367, 2025
@article{wang2025maroesl, title = {{MA-ROESL}: Motion-aware Rapid Reward Optimization for Efficient Robot Skill Learning from Single Videos}, author = {Wang, Xianghui and Zhang, Xinming and Chen, Yanjun and Shen, Xiaoyu and Zhang, Wei}, journal = {arXiv preprint arXiv:2505.08367}, year = {2025}, }
2024
- arXivRethinking Soft Actor-Critic in High-Dimensional Action Spaces: The Cost of Ignoring Distribution ShiftarXiv preprint arXiv:2410.16739, 2024
@article{chen2024sac, title = {Rethinking Soft Actor-Critic in High-Dimensional Action Spaces: The Cost of Ignoring Distribution Shift}, author = {Chen, Yanjun and Zhang, Xinming and Wang, Xianghui and Xu, Zhiqiang and Shen, Xiaoyu and Zhang, Wei}, journal = {arXiv preprint arXiv:2410.16739}, year = {2024}, }