English
Related papers

Related papers: Efficient Context Scaling with LongCat ZigZag Atte…

200 papers

We study continued training and supervised fine-tuning (SFT) of a language model (LM) to make effective use of long-context information. We first establish a reliable evaluation protocol to guide model development -- instead of perplexity…

Computation and Language · Computer Science 2025-12-04 Tianyu Gao , Alexander Wettig , Howard Yen , Danqi Chen

Long-context capability and computational efficiency are among the central challenges facing today's large language models. Existing efficient attention methods reduce computational complexity, but they typically suffer from a limited…

Computation and Language · Computer Science 2026-02-05 Yunao Zheng , Xiaojie Wang , Lei Ren , Wei Chen

As the length of input text increases, the key-value (KV) cache in LLMs imposes prohibitive GPU memory costs and limits long-context inference on resource constrained devices. Existing approaches, such as KV quantization and pruning, reduce…

Machine Learning · Computer Science 2025-12-24 Tenghui Li , Guoxu Zhou , Xuyang Zhao , Yuning Qiu , Qibin Zhao

The ability of Large Language Models (LLMs) to process and generate coherent text is markedly weakened when the number of input tokens exceeds their pretraining length. Given the expensive overhead of finetuning large-scale models with…

Computation and Language · Computer Science 2024-05-30 Chenxin An , Fei Huang , Jun Zhang , Shansan Gong , Xipeng Qiu , Chang Zhou , Lingpeng Kong

Transformer-based architectures have become the prevailing backbone of large language models. However, the quadratic time and memory complexity of self-attention remains a fundamental obstacle to efficient long-context modeling. To address…

Computation and Language · Computer Science 2026-02-10 Yutao Sun , Zhenyu Li , Yike Zhang , Tengyu Pan , Bowen Dong , Yuyi Guo , Jianyong Wang

Multi-headed Attention's (MHA) quadratic compute and linearly growing KV-cache make long-context transformers expensive to train and serve. Prior works such as Grouped Query Attention (GQA) and Multi-Latent Attention (MLA) shrink the cache,…

Computation and Language · Computer Science 2026-03-18 Tomas Figliolia , Nicholas Alonso , Rishi Iyer , Quentin Anthony , Beren Millidge

Large language models spend most of their inference cost on attention over long contexts, yet empirical behavior suggests that only a small subset of tokens meaningfully contributes to each query. We formalize this phenomenon by modeling…

Artificial Intelligence · Computer Science 2026-02-17 Vashista Nobaub

Recent advances in Large Language Models (LLMs) have enabled them to process increasingly longer sequences, ranging from 2K to 2M tokens and even beyond. However, simply extending the input sequence length does not necessarily lead to…

Computation and Language · Computer Science 2025-12-03 Jingyang Lin , Andy Wong , Tian Xia , Shenghua He , Hui Wei , Mei Han , Jiebo Luo

Large reasoning models (LRMs) achieve state-of-the-art performance on challenging benchmarks by generating long chains of intermediate steps, but their inference cost is dominated by decoding, where each new token must attend to the entire…

Computation and Language · Computer Science 2026-05-05 Hossein Entezari Zarch , Lei Gao , Chaoyi Jiang , Murali Annavaram

Reasoning over long contexts is essential for large language models. While reinforcement learning (RL) enhances short-context reasoning by inducing "Aha" moments in chain-of-thought, the advanced thinking patterns required for long-context…

Computation and Language · Computer Science 2025-10-28 Siyuan Wang , Gaokai Zhang , Li Lyna Zhang , Ning Shang , Fan Yang , Dongyao Chen , Mao Yang

We argue that neither transformers nor sub-quadratic architectures are well suited to training at long sequence lengths: the cost of processing the context is too expensive in the former, too inexpensive in the latter. Approaches such as…

Machine Learning · Computer Science 2025-07-08 Carles Gelada , Jacob Buckman , Sean Zhang , Txus Bach

Large language models (LLMs) encounter computational challenges during long-sequence inference, especially in the attention pre-filling phase, where the complexity grows quadratically with the prompt length. Previous efforts to mitigate…

Machine Learning · Computer Science 2025-03-03 Xunhao Lai , Jianqiao Lu , Yao Luo , Yiyuan Ma , Xun Zhou

Long-context understanding is crucial for many NLP applications, yet transformers struggle with efficiency due to the quadratic complexity of self-attention. Sparse attention methods alleviate this cost but often impose static, predefined…

Computation and Language · Computer Science 2025-06-16 Hanzhi Zhang , Heng Fan , Kewei Sha , Yan Huang , Yunhe Feng

Transformer-based models are unable to process long sequences due to their self-attention operation, which scales quadratically with the sequence length. To address this limitation, we introduce the Longformer with an attention mechanism…

Computation and Language · Computer Science 2020-12-03 Iz Beltagy , Matthew E. Peters , Arman Cohan

Most deep trackers still follow the guidance of the siamese paradigms and use a template that contains only the target without any contextual information, which makes it difficult for the tracker to cope with large appearance changes, rapid…

Computer Vision and Pattern Recognition · Computer Science 2023-02-28 Kaijie He , Canlong Zhang , Sheng Xie , Zhixin Li , Zhiwen Wang

This work introduces an efficient method to scale Transformer-based Large Language Models (LLMs) to infinitely long inputs with bounded memory and computation. A key component in our proposed approach is a new attention technique dubbed…

Computation and Language · Computer Science 2024-08-13 Tsendsuren Munkhdalai , Manaal Faruqui , Siddharth Gopal

Block-wise sparse attention offers significant efficiency gains for long-context modeling, yet existing methods often suffer from low selection fidelity and cumulative contextual loss by completely discarding unselected blocks. To address…

Computation and Language · Computer Science 2026-02-02 Bailin Wang , Dan Friedman , Tao Lei , Chong Wang

Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of…

Computation and Language · Computer Science 2019-12-30 Guangxiang Zhao , Junyang Lin , Zhiyuan Zhang , Xuancheng Ren , Qi Su , Xu Sun

Transformer-based architectures traditionally employ softmax to compute attention weights, which produces dense distributions over all tokens in a sequence. While effective in many settings, this density has been shown to be detrimental for…

Computation and Language · Computer Science 2026-03-03 Pavlo Vasylenko , Hugo Pitorro , André F. T. Martins , Marcos Treviso

Block-wise diffusion language models (DLMs) generate multiple tokens in any order, offering a promising alternative to the autoregressive decoding pipeline. However, they still remain bottlenecked by memory-bound attention in long-context…