4 papers
PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects
Sicheng Yang, Shulan Ruan, Shiwei Wu +4
While End-to-End (E2E) Speech-Large Language Models (Speech-LLMs) are rapidly evolving, their evaluation methodologies remain limited to the era of simple transcription. Existing b…
V2X-DSC: Multi-Agent Collaborative Perception with Distributed Source Coding Guided Communication
Yuankun Zeng, Shaohui Li, Zhi Li +3
Collaborative perception improves 3D understanding by fusing multi-agent observations, yet intermediate-feature sharing faces strict bandwidth constraints as dense BEV features sat…
From Observations to Events: Event-Aware World Model for Reinforcement Learning
Zhao-Han Peng, Shaohui Li, Zhi Li +3
While model-based reinforcement learning (MBRL) improves sample efficiency by learning world models from raw observations, existing methods struggle to generalize across structural…
GaLore: Boosting Low-Rank Adaptation for LLMs with Cross-Head Projection
Xutao Liao, Shaohui Li, Yuhui Xu +3
Recent low-rank training methods, such as GaLore, have significantly reduced the memory required to optimize large language models (LLMs). However, these methods often suffer from…