1

Can LLMs Reason Soundly in Law? Auditing Inference Patterns for Legal Judgment
This paper presents a method to analyze the inference patterns used by Large Language Models (LLMs) for judgment in a case study on …
Lu Chen, Yuxuan Huang, Yixing Li, Dongrui Liu, Qihan Ren, ShuaiZhao, Kun Kuang, Zilong Zheng, Quanshi Zhang
Posted Apr 25, 2026
Link to ICLR
Can LLMs Reason Soundly in Law? Auditing Inference Patterns for Legal Judgment
Transmamba: Flexibly switching between transformer and mamba
Transformers are the cornerstone of modern large language models, but their quadratic computational complexity limits efficiency in …
Yixing Li, Ruobing Xie, Zhen Yang, Xingwu Sun, Shuaipeng Li, Weidong Han, Zhanhui Kang, Yu Cheng, Chengzhong Xu, Di Wang, Jie Jiang
Posted Jan 7, 2026
Link to arxiv Link to AAAI
Transmamba: Flexibly switching between transformer and mamba
Continuous Speech Tokenizer in Text To Speech
The fusion of speech and language in the era of large language models has garnered significant attention. Discrete speech token is …
Yixing Li, Ruobing Xie, Xingwu Sun, Yu Cheng, Zhanhui Kang
Posted May 4, 2025
Link to NAACL
Continuous Speech Tokenizer in Text To Speech
Scaling Laws for Floating Point Quantization Training
Low-precision training is considered an effective strategy for reducing both training and downstream inference costs. Previous scaling …
Xingwu Sun, Shuaipeng Li, Ruobing Xie, Et.al.
Posted Jan 4, 2025
Link to arxiv Link to ICML
Scaling Laws for Floating Point Quantization Training
From isolated islands to pangea: Unifying semantic space for human action understanding
Action understanding matters for intelligent agents and has attracted long-term attention. It can be formed as the mapping from the …
YongLu Li, Xiaoqian Wu, Xinpeng Liu, Et.al
Posted Apr 3, 2024
Link to arxiv Link to CVPR
From isolated islands to pangea: Unifying semantic space for human action understanding