5 papers
Sandboxed Coding Agents are Competitive Omni-modal Task Solvers
Dongping Chen, Xuanao Huang, Zhihan Hu +3
As multimodal LLMs increasingly target video and audio, it is often assumed that such tasks require native omnimodal models. We show that this is not always the case: coding agents…
TAPO: Translation Augmented Policy Optimization for Multilingual Mathematical Reasoning
Xu Huang, Zhejian Lai, Zixian Huang +2
Large Language Models (LLMs) have demonstrated remarkable proficiency in English mathematical reasoning, yet a significant performance disparity persists in multilingual contexts,…
BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models
Xu Huang, Wenhao Zhu, Hanxu Hu +4
Previous multilingual benchmarks focus primarily on simple understanding tasks, but for large language models(LLMs), we emphasize proficiency in instruction following, reasoning, l…
Could Thinking Multilingually Empower LLM Reasoning?
Changjiang Gao, Xu Huang, Wenhao Zhu +3
Previous work indicates that large language models exhibit a significant "English bias", i.e. they often perform better when tasks are presented in English. Interestingly, we have…
Communication-Efficient Personalized Federated Learning for Speech-to-Text Tasks
Yichao Du, Zhirui Zhang, Linan Yue +5
To protect privacy and meet legal regulations, federated learning (FL) has gained significant attention for training speech-to-text (S2T) systems, including automatic speech recogn…