Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Haojie Lu

Haojie Lu

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2Sound×1

Frequent co-authors

Yuxuan Wu1×
Yifan Xu1×
Junkun Wang1×
Jiayong Jiang1×
Xin Zhao1×
Zhaojie Luo1×

Research Timeline

2026
Deconstructing Spatial Complexity: Hierarchical Decomposition for LLM Spatial Reasoning

This paper introduces MCTS-Guided Group Relative Policy Optimization (M-GRPO) to enhance LLM spatial reasoning by improving the decomposition of complex tasks into optimal sub-tasks.

Re-Sonance: A Dysarthric Asynchronous Real-Time Speech Conversion System Based on a Three-Stage Cascaded ASR-LLM-TTS Architecture

This paper introduces Re-Sonance, a real-time speech-driven AAC system for professional speaking scenarios using LLM-enhanced Whisper ASR, Qwen LLM, and CosyVoice TTS.

Highlighted terms show continued research focus across papers

Papers

cs.SDcs.AIEmpiricalRecentJul 20, 2026

Re-Sonance: A Dysarthric Asynchronous Real-Time Speech Conversion System Based on a Three-Stage Cascaded ASR-LLM-TTS Architecture

Yuxuan Wu, Yifan Xu, Junkun Wang, Jiayong Jiang +2 more

This paper introduces Re-Sonance, a real-time speech-driven AAC system for professional speaking scenarios using LLM-enhanced Whisper ASR, Qwen LLM, and CosyVoice TTS.

View →
cs.AIRecentMay 27, 2026

Deconstructing Spatial Complexity: Hierarchical Decomposition for LLM Spatial Reasoning

Yi Wang, Haojie Lu, Zhaofan Zhang, Li Chen +1 more

This paper introduces MCTS-Guided Group Relative Policy Optimization (M-GRPO) to enhance LLM spatial reasoning by improving the decomposition of complex tasks into optimal sub-tasks.

View →