activity
20222024
most citedLongNet: Scaling Transformers to 1,000,000,000 Tokens

36 citations · 67 across the 7 of their papers we have counts for

collaborators

7 papers

cs.CL20246 cited

Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models

Haoran Li, Qingxiu Dong, Zhengyang Tang +17

We introduce Generalized Instruction Tuning (called GLAN), a general and scalable method for instruction tuning of Large Language Models (LLMs). Unlike prior work that relies on se…

cs.LG2023

Unleashing the potential of GNNs via Bi-directional Knowledge Transfer

Shuai Zheng, Zhizhe Liu, Zhenfeng Zhu +3

Based on the message-passing paradigm, there has been an amount of research proposing diverse and impressive feature propagation mechanisms to improve the performance of GNNs. Howe…

cs.CL20231 cited

Tuna: Instruction Tuning using Feedback from Large Language Models

Haoran Li, Yiran Liu, Xingxing Zhang +2

Instruction tuning of open-source large language models (LLMs) like LLaMA, using direct outputs from more powerful LLMs such as Instruct-GPT and GPT-4, has proven to be a cost-effe…

cs.LG20233 cited

Overcoming Recency Bias of Normalization Statistics in Continual Learning: Balance and Adaptation

Yilin Lyu, Liyuan Wang, Xingxing Zhang +4

Continual learning entails learning a sequence of tasks and balancing their knowledge appropriately. With limited access to old training samples, much of the current work in deep n…

cs.LG202318 cited

Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality

Liyuan Wang, Jingyi Xie, Xingxing Zhang +3

Prompt-based continual learning is an emerging direction in leveraging pre-trained knowledge for downstream continual learning, and has almost reached the performance pinnacle unde…

cs.CL202336 cited

LongNet: Scaling Transformers to 1,000,000,000 Tokens

Jiayu Ding, Shuming Ma, Li Dong +5

Scaling sequence length has become a critical demand in the era of large language models. However, existing methods struggle with either computational complexity or model expressiv…