English
Related papers

Related papers: ActTail: Global Activation Sparsity in Large Langu…

200 papers

Large Language Models (LLMs) face significant computational bottlenecks during inference due to the quadratic complexity of self-attention mechanisms, particularly as context lengths increase. We introduce SpecAttn, a novel training-free…

Computation and Language · Computer Science 2025-11-03 Harsh Shah

The impressive performance of Large Language Models (LLMs) across various natural language processing tasks comes at the cost of vast computational resources and storage requirements. One-shot pruning techniques offer a way to alleviate…

Machine Learning · Computer Science 2025-09-09 Xiang Meng , Kayhan Behdin , Haoyue Wang , Rahul Mazumder

Large Language Models (LLMs) have demonstrated remarkable capabilities across various applications, but their performance on long-context tasks is often limited by the computational complexity of attention mechanisms. We introduce a novel…

Machine Learning · Computer Science 2025-02-25 Bo Chen , Yingyu Liang , Zhizhou Sha , Zhenmei Shi , Zhao Song

Top-k sparsification has recently been widely used to reduce the communication volume in distributed deep learning. However, due to the Sparse Gradient Accumulation (SGA) dilemma, the performance of top-k sparsification still has…

Machine Learning · Computer Science 2024-02-26 Minjun Zhao , Yichen Yin , Yuren Mao , Qing Liu , Lu Chen , Yunjun Gao

Aligning general-purpose large language models (LLMs) to downstream tasks often incurs significant training adjustment costs. Prior research has explored various avenues to enhance alignment efficiency, primarily through minimal-data…

Computation and Language · Computer Science 2025-06-19 Hao Chen , Haoze Li , Zhiqing Xiao , Lirong Gao , Qi Zhang , Xiaomeng Hu , Ningtao Wang , Xing Fu , Junbo Zhao

This study aims to explore the performance improvement method of large language models based on GPT-4 under the multi-task learning framework and conducts experiments on two tasks: text classification and automatic summary generation.…

Computation and Language · Computer Science 2024-12-10 Zhen Qi , Jiajing Chen , Shuo Wang , Bingying Liu , Hongye Zheng , Chihang Wang

The growing computational demands of large language models (LLMs) make efficient inference and activation strategies increasingly critical. While recent approaches, such as Mixture-of-Experts (MoE), leverage selective activation but require…

Machine Learning · Computer Science 2026-02-19 Sihan Chen , Dan Zhao , Jongwoo Ko , Colby Banbury , Huiping Zhuang , Luming Liang , Pashmina Cameron , Tianyi Chen

The high power consumption and latency-sensitive deployments of large language models (LLMs) have motivated efficiency techniques like quantization and sparsity. Contextual sparsity, where the sparsity pattern is input-dependent, is crucial…

Low-rank and sparse composite approximation is a natural idea to compress Large Language Models (LLMs). However, such an idea faces two primary challenges that adversely affect the performance of existing methods. The first challenge…

Machine Learning · Computer Science 2026-02-27 Changhai Zhou , Qian Qiao , Yuhua Zhou , Yuxin Wu , Shichao Weng , Weizhong Zhang , Cheng Jin

Procedural activity videos often exhibit a long-tailed action distribution due to varying action frequencies and durations. However, state-of-the-art temporal action segmentation methods overlook the long tail and fail to recognize tail…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Zhanzhong Pang , Fadime Sener , Shrinivas Ramasubramanian , Angela Yao

Despite the successes of probabilistic models based on passing noise through neural networks, recent work has identified that such methods often fail to capture tail behavior accurately, unless the tails of the base distribution are…

Machine Learning · Statistics 2023-06-16 Feynman Liang , Liam Hodgkinson , Michael W. Mahoney

Modern large language models (LLMs) place extraordinary pressure on memory and compute budgets, making principled compression indispensable for both deployment and continued training. We present Hierarchical Sparse Plus Low-Rank (HSS)…

Machine Learning · Computer Science 2026-01-14 Pawan Kumar , Aditi Gupta

Due to the lack of temporal annotation, current Weakly-supervised Temporal Action Localization (WTAL) methods are generally stuck into over-complete or incomplete localization. In this paper, we aim to leverage the text information to boost…

Computer Vision and Pattern Recognition · Computer Science 2023-05-02 Guozhang Li , De Cheng , Xinpeng Ding , Nannan Wang , Xiaoyu Wang , Xinbo Gao

Recently, sparse autoencoders (SAEs) have emerged as a promising technique for interpreting activations in foundation models by disentangling features into a sparse set of concepts. However, identifying the optimal level of sparsity for…

Machine Learning · Computer Science 2026-04-17 Dongsheng Wang , Jinsen Zhang , Dawei Su , Hui Huang

Robust Bayesian methods for high-dimensional regression problems under diverse sparse regimes are studied. Traditional shrinkage priors are primarily designed to detect a handful of signals from tens of thousands of predictors in the…

Statistics Theory · Mathematics 2024-10-25 Se Yoon Lee , Peng Zhao , Debdeep Pati , Bani K. Mallick

Leveraging attention sparsity to accelerate long-context large language models (LLMs) has been a hot research topic. However, current algorithms such as sparse attention or key-value (KV) cache compression tend to use a fixed budget, which…

Machine Learning · Computer Science 2025-11-05 Chaofan Lin , Jiaming Tang , Shuo Yang , Hanshuo Wang , Tian Tang , Boyu Tian , Ion Stoica , Song Han , Mingyu Gao

While sparse attention mitigates the computational bottleneck of long-context LLM training, its distributed training process exhibits extreme heterogeneity in both \textit{1)} sequence length and \textit{2)} sparsity sensitivity, leading to…

Machine Learning · Computer Science 2026-04-27 Hongtao Xu , Jianchao Tan , Yuxuan Hu , Pengju Lu , Hongyu Wang , Pingwei Sun , Yerui Sun , Yuchen Xie , Xunliang Cai , Mingzhen Li , Weile Jia

Attention serves as the fundamental mechanism for long-context modeling in large language models (LLMs), yet dense attention becomes structurally prohibitive for long sequences due to its quadratic complexity. Consequently, sparse attention…

Computation and Language · Computer Science 2026-01-07 Junxiang Qiu , Shuo Wang , Zhengsu Chen , Hengheng Zhang , Jinda Lu , Changcheng Li , Qi Tian

Neurons process sensory stimuli efficiently, showing sparse yet highly variable ensemble spiking activity involving structured higher-order interactions. Notably, while neural populations are mostly silent, they occasionally exhibit highly…

Neurons and Cognition · Quantitative Biology 2025-07-17 Ulises Rodríguez-Domínguez , Hideaki Shimazaki

A growing intuition in machine learning suggests a link between sparsity and interpretability. We introduce a novel self-ablation mechanism to investigate this connection ante-hoc in the context of language transformers. Our approach…

Machine Learning · Computer Science 2025-05-02 Jeremias Ferrao , Luhan Mikaelson , Keenan Pepper , Natalia Perez-Campanero Antolin