4 papers
LaDA-Band: Language Diffusion Models for Vocal-to-Accompaniment Generation
Qi Wang, Zhexu Shen, Meng Chen +4
Vocal-to-accompaniment (V2A) generation, which aims to transform a raw vocal recording into a fully arranged accompaniment, inherently requires jointly addressing an accompaniment…
Reasoning Pattern Matters: Learning to Reason without Human Rationales
Chaoxu Pang, Yixuan Cao, Ping Luo
Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities under the widely adopted SFT+RLVR paradigm, which first performs Supervised Fine-Tuning (SFT) on hu…
Document-Level Tabular Numerical Cross-Checking: A Coarse-to-Fine Approach
Chaoxu Pang, Yixuan Cao, Ganbin Zhou +2
Numerical consistency across tables in disclosure documents is critical for ensuring accuracy, maintaining credibility, and avoiding reputational and economic risks. Automated tabu…
Uncovering Limitations of Large Language Models in Information Seeking from Tables
Chaoxu Pang, Yixuan Cao, Chunhao Yang +1
Tables are recognized for their high information density and widespread usage, serving as essential sources of information. Seeking information from tables (TIS) is a crucial capab…