English
Related papers

Related papers: MTraining: Distributed Dynamic Sparse Attention fo…

200 papers

Recent advancements in LLM pretraining have featured ever-expanding context windows to process longer sequences. However, our pilot study reveals that models pretrained with shorter context windows consistently outperform their long-context…

Computation and Language · Computer Science 2025-12-03 Tongyao Zhu , Qian Liu , Haonan Wang , Shiqi Chen , Xiangming Gu , Tianyu Pang , Min-Yen Kan

Sparsity-aware training is an effective approach for transforming large language models (LLMs) into hardware-friendly sparse patterns, thereby reducing latency and memory consumption during inference. In this paper, we propose Continuous…

Machine Learning · Computer Science 2025-10-01 Weiyu Huang , Yuezhou Hu , Jun Zhu , Jianfei Chen

Embedding models play a pivot role in modern NLP applications such as IR and RAG. While the context limit of LLMs has been pushed beyond 1 million tokens, embedding models are still confined to a narrow context window not exceeding 8k…

Computation and Language · Computer Science 2024-11-08 Dawei Zhu , Liang Wang , Nan Yang , Yifan Song , Wenhao Wu , Furu Wei , Sujian Li

Long context understanding remains challenging for large language models due to their limited context windows. This paper introduces Long Input Fine-Tuning (LIFT), a novel framework for long-context modeling that can enhance the…

Computation and Language · Computer Science 2026-04-14 Yansheng Mao , Yufei Xu , Jiaqi Li , Fanxu Meng , Haotong Yang , Zilong Zheng , Xiyuan Wang , Muhan Zhang

Managing long sequences has become an important and necessary feature for large language models (LLMs). However, it is still an open question of how to comprehensively and systematically evaluate the long-sequence capability of LLMs. One of…

Computation and Language · Computer Science 2024-07-30 Wai-Chung Kwan , Xingshan Zeng , Yufei Wang , Yusen Sun , Liangyou Li , Lifeng Shang , Qun Liu , Kam-Fai Wong

Efficient parallelization of Large Language Models (LLMs) with long sequences is essential but challenging due to their significant computational and memory demands, particularly stemming from communication bottlenecks in attention…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-12-31 Zongwu Wang , Fangxin Liu , Mingshuai Li , Li Jiang

AI accelerator processing capabilities and memory constraints largely dictate the scale in which machine learning workloads (e.g., training and inference) can be executed within a desirable time frame. Training a state of the art,…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-10-12 Michael Benington , Leo Phan , Chris Pierre Paul , Evan Shoemaker , Priyanka Ranade , Torstein Collett , Grant Hodgson Perez , Christopher Krieger

The limited context window of contemporary large language models (LLMs) remains a primary bottleneck for their broader application across diverse domains. Although continual pre-training on long-context data offers a straightforward…

Computation and Language · Computer Science 2026-04-10 Wei Han , Pan Zhou , Soujanya Poria , Shuicheng Yan

We propose a novel, efficient approach for distributed sparse learning in high-dimensions, where observations are randomly partitioned across machines. Computationally, at each round our method only requires the master machine to solve a…

Machine Learning · Statistics 2016-05-26 Jialei Wang , Mladen Kolar , Nathan Srebro , Tong Zhang

Scaling neural networks has driven breakthrough advances in machine learning, yet this paradigm fails in deep reinforcement learning (DRL), where larger models often degrade performance due to unique optimization pathologies such as…

Machine Learning · Computer Science 2025-10-15 Guozheng Ma , Lu Li , Zilin Wang , Haoyu Wang , Shengchao Hu , Leszek Rutkowski , Dacheng Tao

We present MM1.5, a new family of multimodal large language models (MLLMs) designed to enhance capabilities in text-rich image understanding, visual referring and grounding, and multi-image reasoning. Building upon the MM1 architecture,…

This paper presents meta-sparsity, a framework for learning model sparsity, basically learning the parameter that controls the degree of sparsity, that allows deep neural networks (DNNs) to inherently generate optimal sparse shared…

Machine Learning · Computer Science 2025-01-22 Richa Upadhyay , Ronald Phlypo , Rajkumar Saini , Marcus Liwicki

Multimodal Large Language Models (MLLMs) suffer from severe training inefficiency issue, which is associated with their massive model sizes and visual token numbers. Existing efforts in efficient training focus on reducing model sizes or…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Dingkun Zhang , Shuhan Qi , Yulin Wu , Xinyu Xiao , Xuan Wang , Long Chen

Large language models (LLMs) have made significant strides in complex tasks, yet their widespread adoption is impeded by substantial computational demands. With hundreds of billion parameters, transformer-based LLMs necessitate months of…

Machine Learning · Computer Science 2024-08-22 Pihe Hu , Shaolong Li , Longbo Huang

In long-context large language model (LLM) inference, the prefill stage dominates computation due to self-attention over the complete input context. Sparse attention significantly reduces self-attention computation by limiting each token's…

Hardware Architecture · Computer Science 2026-02-25 Rakshith Jayanth , Viktor Prasanna

Training large models requires a large amount of data, as well as abundant computation resources. While collaborative learning (e.g., federated learning) provides a promising paradigm to harness collective data from many participants,…

Machine Learning · Computer Science 2024-07-08 Jin Xie , Songze Li

Large language models (LLMs) now support extremely long context windows, but the quadratic complexity of vanilla attention results in significantly long Time-to-First-Token (TTFT) latency. Existing approaches to address this complexity…

Computation and Language · Computer Science 2025-09-04 Qianchao Zhu , Jiangfei Duan , Chang Chen , Siran Liu , Guanyu Feng , Xin Lv , Xiao Chuanfu , Dahua Lin , Chao Yang

Serving long-context LLMs is costly because attention computation grows linearly with context length. Dynamic sparse attention algorithms (DSAs) mitigate this by attending only to the key-value (KV) cache of critical tokens. However, with…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-30 Qihui Zhou , Peiqi Yin , Pengfei Zuo , James Cheng

Reinforcement Learning has emerged as a key driver for LLM reasoning. This capability is equally pivotal in long-context scenarios--such as long-dialogue understanding and structured data analysis, where the challenge extends beyond…

Computation and Language · Computer Science 2026-02-06 Bowen Ping , Zijun Chen , Yiyao Yu , Tingfeng Hui , Junchi Yan , Baobao Chang

Large language models (LLMs) are commonly trained on datasets consisting of fixed-length token sequences. These datasets are created by randomly concatenating documents of various lengths and then chunking them into sequences of a…

Computation and Language · Computer Science 2025-01-08 Hadi Pouransari , Chun-Liang Li , Jen-Hao Rick Chang , Pavan Kumar Anasosalu Vasu , Cem Koc , Vaishaal Shankar , Oncel Tuzel