activity
20212025
most citedMoDS: Model-oriented Data Selection for Instruction Tuning

4 citations · 14 across the 10 of their papers we have counts for

collaborators
Showing cs.CLShow all

10 papers · 1 filter

cs.CL2025

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…

cs.CL2025

Group then Scale: Dynamic Mixture-of-Experts Multilingual Language Model

Chong Li, Yingzhuo Deng, Jiajun Zhang +1

The curse of multilinguality phenomenon is a fundamental problem of multilingual Large Language Models (LLMs), where the competition between massive languages results in inferior p…

cs.CL2025

TokAlign: Efficient Vocabulary Adaptation via Token Alignment

Chong Li, Jiajun Zhang, Chengqing Zong

Tokenization serves as a foundational step for Large Language Models (LLMs) to process text. In new domains or languages, the inefficiency of the tokenizer will slow down the train…

cs.CL20234 cited

MoDS: Model-oriented Data Selection for Instruction Tuning

Qianlong Du, Chengqing Zong, Jiajun Zhang

Instruction tuning has become the de facto method to equip large language models (LLMs) with the ability of following user instructions. Usually, hundreds of thousands or millions…

cs.CL20221 cited

Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation

Chen Wang, Yuchen Liu, Boxing Chen +4

End-to-end Speech Translation (ST) aims at translating the source language speech into target language text without generating the intermediate transcriptions. However, the trainin…

cs.CL20221 cited

Other Roles Matter! Enhancing Role-Oriented Dialogue Summarization via Role Interactions

Haitao Lin, Junnan Zhu, Lu Xiang +3

Role-oriented dialogue summarization is to generate summaries for different roles in the dialogue, e.g., merchants and consumers. Existing methods handle this task by summarizing e…