5 papers
How to Use Parallel Data for Multilingual Pretraining
Zhihong Huang, Yao Lu, Derek F. Wong +2
High-quality human-translated parallel corpora can improve cross-lingual transfer, but are typically too small for large-scale pretraining. Machine-translated web corpora help over…
Beyond Quantity: Trajectory Diversity Scaling for Code Agents
Guhong Chen, Chenghao Sun, Cheng Fu +16
As code large language models (LLMs) evolve into tool-interactive agents via the Model Context Protocol (MCP), their generalization is increasingly limited by low-quality synthetic…
Robust and Efficient Zeroth-Order LLM Fine-Tuning via Adaptive Bayesian Subspace Optimizer
Jian Feng, Zhihong Huang
Fine-tuning large language models (LLMs) with zeroth-order (ZO) optimization reduces memory by approximating gradients through function evaluations. However, existing methods essen…
Are Large Reasoning Models Good Translation Evaluators? Analysis and Performance Boost
Runzhe Zhan, Zhihong Huang, Xinyi Yang +3
Recent advancements in large reasoning models (LRMs) have introduced an intermediate "thinking" process prior to generating final answers, improving their reasoning capabilities on…
How Does Pretraining Improve Discourse-Aware Translation?
Zhihong Huang, Longyue Wang, Siyou Liu +1
Pretrained language models (PLMs) have produced substantial improvements in discourse-aware neural machine translation (NMT), for example, improved coherence in spoken language tra…