activity
20242026
most citedWhen Attention Sink Emerges in Language Models: An Empirical View

2 citations · 3 across the 10 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL20251 cited

Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs

Longxu Dou, Qian Liu, Fan Zhou +38

Sailor2 is a family of cutting-edge multilingual language models for South-East Asian (SEA) languages, available in 1B, 8B, and 20B sizes to suit diverse applications. Building on…

cs.CL2025

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification

Penghui Yang, Cunxiao Du, Fengzhuo Zhang +4

As Large Language Models (LLMs) can now process extremely long contexts, efficient inference over these extended inputs has become increasingly important, especially for emerging a…

cs.CL2024

When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training

Haonan Wang, Qian Liu, Chao Du +4

Extending context window sizes allows large language models (LLMs) to process longer sequences and handle more complex tasks. Rotary Positional Embedding (RoPE) has become the de f…

cs.CL2024

LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation

Xuan Zhang, Fengzhuo Zhang, Cunxiao Du +4

Scaling language models to handle longer contexts introduces substantial memory challenges due to the growing cost of key-value (KV) caches. Motivated by the efficiency gains of hy…

cs.CL20242 cited

When Attention Sink Emerges in Language Models: An Empirical View

Xiangming Gu, Tianyu Pang, Chao Du +5

Language Models (LMs) assign significant attention to the first token, even if it is not semantically important, which is known as attention sink. This phenomenon has been widely a…

cs.CL2024

Reverse Modeling in Large Language Models

Sicheng Yu, Yuanchen Xu, Cunxiao Du +5

Humans are accustomed to reading and writing in a forward manner, and this natural bias extends to text understanding in auto-regressive large language models (LLMs). This paper in…