Showing 2025Show all
3 papers · 1 filter
cs.LG2025
Think Smart, Not Hard: Difficulty Adaptive Reasoning for Large Audio Language Models
Zhichao Sheng, Shilin Zhou, Chen Gong +1
Large Audio Language Models (LALMs), powered by the chain-of-thought (CoT) paradigm, have shown remarkable reasoning capabilities. Intuitively, different problems often require var…
eess.AS2025
UniSLU: Unified Spoken Language Understanding from Heterogeneous Cross-Task Datasets
Zhichao Sheng, Shilin Zhou, Chen Gong +1
Spoken Language Understanding (SLU) plays a crucial role in speech-centric multimedia applications, enabling machines to comprehend spoken language in scenarios such as meetings, i…
cs.CL2025
Self-Correction Makes LLMs Better Parsers
Ziyan Zhang, Yang Hou, Chen Gong +1
Large language models (LLMs) have achieved remarkable success across various natural language processing (NLP) tasks. However, recent studies suggest that they still face challenge…