10 papers · 1 filter
Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs
Zixuan Ren, Jinliang Lu, Junhong Wu +5
Model merging plays a crucial role in consolidating multiple specialized models into a single, unified model, especially in the era of large language models (LLMs). Recent research…
LADM: Long-context Training Data Selection with Attention-based Dependency Measurement for LLMs
Jianghao Chen, Junhong Wu, Yangyifan Xu +1
Long-context modeling has drawn more and more attention in the area of Large Language Models (LLMs). Continual training with long-context data becomes the de-facto method to equip…
Parallel Scaling Law: Unveiling Reasoning Generalization through A Cross-Linguistic Perspective
Wen Yang, Junhong Wu, Chong Li +2
Recent advancements in Reinforcement Post-Training (RPT) have significantly enhanced the capabilities of Large Reasoning Models (LRMs), sparking increased interest in the generaliz…
Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment
Wen Yang, Junhong Wu, Chen Wang +2
Direct Preference Optimization (DPO) has become a prominent method for aligning Large Language Models (LLMs) with human preferences. While DPO has enabled significant progress in a…
Language Imbalance Driven Rewarding for Multilingual Self-improving
Wen Yang, Junhong Wu, Chen Wang +2
Large Language Models (LLMs) have achieved state-of-the-art performance across numerous tasks. However, these advancements have predominantly benefited "first-class" languages such…
F-MALLOC: Feed-forward Memory Allocation for Continual Learning in Neural Machine Translation
Junhong Wu, Yuchen Liu, Chengqing Zong
In the evolving landscape of Neural Machine Translation (NMT), the pretrain-then-finetune paradigm has yielded impressive results. However, the persistent challenge of Catastrophic…