activity
20242026
most citedMiniLLM: On-Policy Distillation of Large Language Models

20 citations · 20 across the 2 of their papers we have counts for

collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL202620 cited

MiniLLM: On-Policy Distillation of Large Language Models

Yuxian Gu, Li Dong, Furu Wei +1

Knowledge Distillation (KD) is a promising technique for reducing the high computational demand of large language models (LLMs). However, previous KD methods are primarily applied…

cs.CL2025

Differential Transformer

Tianzhu Ye, Li Dong, Yuqing Xia +4

Transformer tends to overallocate attention to irrelevant context. In this work, we introduce Diff Transformer, which amplifies attention to the relevant context while canceling no…

cs.CL2025

Direct Preference Knowledge Distillation for Large Language Models

Yixing Li, Yuxian Gu, Li Dong +3

In the field of large language models (LLMs), Knowledge Distillation (KD) is a critical technique for transferring capabilities from teacher models to student models. However, exis…

cs.CL2024

Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models

Wenshan Wu, Shaoguang Mao, Yadong Zhang +4

Large language models (LLMs) have exhibited impressive performance in language comprehension and various reasoning tasks. However, their abilities in spatial reasoning, a crucial a…

cs.CL2024

Self-Boosting Large Language Models with Synthetic Preference Data

Qingxiu Dong, Li Dong, Xingxing Zhang +2

Through alignment with human preferences, Large Language Models (LLMs) have advanced significantly in generating honest, harmless, and helpful responses. However, collecting high-q…

cs.CL2024

KOSMOS-2.5: A Multimodal Literate Model

Tengchao Lv, Yupan Huang, Jingye Chen +13

The automatic reading of text-intensive images represents a significant advancement toward achieving Artificial General Intelligence (AGI). In this paper we present KOSMOS-2.5, a m…