Get started
Author

Dachuan Shi

Priority-Preserving Advantage Aggregation for Multi-Reward Policy Optimization
2026 · Yuan, Xiangchi, Diao, Xingjian, et al. · arXiv (Cornell University)
PDF
PhysAI: An architecture for situated physical judgement
2026 · Agrafiotis, Ioannis, Alexopoulos, Kosmas, et al. · Publication Server of FIR e. V. an der RWTH Aachen
PDF
PACT: Privileged Trace Co-Training for Multi-Turn Tool-Use Agents
2026 · Du, Zhenbang, Luo, Jun, et al. · arXiv (Cornell University)
PDF
Behavior Knowledge Merge in Reinforced Agentic Models
2026 · Association for Computational Linguistics 2026, Lee, Wenke, et al. · Underline Science Inc.
CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning
2026 · Shi, Dachuan, Zhu, Hanlin, et al. · arXiv (Cornell University)
PDF
Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding
2026 · Xu, Zhongxing, Wang, Zhonghua, et al. · arXiv (Cornell University)
PDF
MetaState: Persistent Working Memory Enhances Reasoning in Discrete Diffusion Language Models
2026 · Xia, Kejing, Li, Mingzhe, et al. · arXiv (Cornell University)
PDF
Behavior Knowledge Merge in Reinforced Agentic Models
2026 · Yuan, Xiangchi, Shi, Dachuan, et al. · arXiv (Cornell University)
PDF
Behavior Knowledge Merge in Reinforced Agentic Models
2026 · Xiangchi Yuan, Dachuan Shi, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
2025 · Shi, Dachuan, Asi, Abedelkadir, et al. · arXiv (Cornell University)
PDF
Works count: 10
Citation count:
H-index:
I10-index:
Year
Topic
Type