English
Related papers

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

200 papers

Large language models (LLMs) demonstrate strong capabilities across a wide range of complex tasks and are increasingly deployed at scale, placing significant demands on inference efficiency. Prior work typically decomposes inference into…

Computation and Language · Computer Science 2026-04-21 Junhao Hu , Fangze Li , Mingtao Xu , Feifan Meng , Shiju Zhao , Tiancheng Hu , Ting Peng , Anmin Liu , Wenrui Huang , Chenxu Liu , Ziyue Hua , Tao Xie

Large language models (LLMs) often struggle with strict memory, latency, and power demands. To meet these demands, various forms of dynamic sparsity have been proposed that reduce compute on an input-by-input basis. These methods improve…

Computation and Language · Computer Science 2024-04-09 Jordan Dotzel , Yash Akhauri , Ahmed S. AbouElhamayed , Carly Jiang , Mohamed Abdelfattah , Zhiru Zhang

Diffusion Transformers (DiTs) set the state of the art in visual generation, yet their quadratic self-attention cost fundamentally limits scaling to long token sequences. Recent Top-K sparse attention approaches reduce the computation of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Yifan Zhou , Zeqi Xiao , Tianyi Wei , Shuai Yang , Xingang Pan

Dynamic Sparse Training (DST) methods achieve state-of-the-art results in sparse neural network training, matching the generalization of dense models while enabling sparse training and inference. Although the resulting models are highly…

Machine Learning · Computer Science 2024-02-23 Mike Lasby , Anna Golubeva , Utku Evci , Mihai Nica , Yani Ioannou

We introduce, Q-Sparse, a simple yet effective approach to training sparsely-activated large language models (LLMs). Q-Sparse enables full sparsity of activations in LLMs which can bring significant efficiency gains in inference. This is…

Computation and Language · Computer Science 2024-07-25 Hongyu Wang , Shuming Ma , Ruiping Wang , Furu Wei

The demand for efficient large language model (LLM) inference has intensified the focus on sparsification techniques. While semi-structured (N:M) pruning is well-established for weights, its application to activation pruning remains…

Large Language Models (LLMs) are increasingly prevalent in the field of long-context modeling, however, their inference computational costs have become a critical bottleneck hindering the advancement of tasks such as agents and multimodal…

Computation and Language · Computer Science 2025-12-04 Di Xiu , Hongyin Tang , Bolin Rong , Lizhi Yan , Jingang Wang , Yifan Lu , Xunliang Cai

Training Transformer models on long sequences in a distributed setting poses significant challenges in terms of efficiency and scalability. Current methods are either constrained by the number of attention heads or excessive communication…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-30 Ziming Liu , Shaoyu Wang , Shenggan Cheng , Zhongkai Zhao , Kai Wang , Xuanlei Zhao , James Demmel , Yang You

Spatio-Temporal Scene Graphs (STSGs) provide a concise and expressive representation of dynamic scenes by modeling objects and their evolving relationships over time. However, real-world visual relationships often exhibit a long-tailed…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Rohith Peddi , Saurabh , Ayush Abhay Shrivastava , Parag Singla , Vibhav Gogate

We introduce TAM-RL (Task Aware Modulation using Representation Learning), a novel multimodal meta-learning framework for few-shot learning in heterogeneous systems, designed for science and engineering problems where entities share a…

Machine Learning · Computer Science 2024-10-17 Arvind Renganathan , Rahul Ghosh , Ankush Khandelwal , Vipin Kumar

Large Vision-Language Models (LVLMs) have achieved significant progress in combining visual comprehension with language generation. Despite this success, the training data of LVLMs still suffers from Long-Tail (LT) problems, where the data…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Mingyang Song , Xiaoye Qu , Jiawei Zhou , Yu Cheng

Temporal Action Localization (TAL) requires identifying both the boundaries and categories of actions in untrimmed videos. While vision-language models (VLMs) offer rich semantics to complement visual evidence, existing approaches tend to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Jiaqi Li , Guangming Wang , Shuntian Zheng , Minzhe Ni , Xiaoman Lu , Guanghui Ye , Yu Guan

Activation Patching is a method of directly computing causal attributions of behavior to model components. However, applying it exhaustively requires a sweep with cost scaling linearly in the number of model components, which can be…

Machine Learning · Computer Science 2024-03-04 János Kramár , Tom Lieberum , Rohin Shah , Neel Nanda

We study two strange phenomena in auto-regressive Transformers: (1) the dominance of the first token in attention heads; (2) the occurrence of large outlier activations in the hidden states. We find that popular large language models, such…

Computation and Language · Computer Science 2024-10-23 Prannay Kaul , Chengcheng Ma , Ismail Elezi , Jiankang Deng

Temporal Action Detection (TAD) is an essential and challenging topic in video understanding, aiming to localize the temporal segments containing human action instances and predict the action categories. The previous works greatly rely upon…

Computer Vision and Pattern Recognition · Computer Science 2021-09-21 Jiannan Wu , Peize Sun , Shoufa Chen , Jiewen Yang , Zihao Qi , Lan Ma , Ping Luo

Sparse attention mechanisms aim to reduce computational overhead with minimal accuracy loss by selectively processing salient tokens. Despite their effectiveness, most methods merely exploit a model's inherent sparsity and thus plateau at…

Machine Learning · Computer Science 2026-03-02 Feng Chen , Yefei He , Lequan Lin , Chenhui Gou , Jing Liu , Bohan Zhuang , Qi Wu

Dense large language models(LLMs) face critical efficiency bottlenecks as they rigidly activate all parameters regardless of input complexity. While existing sparsity methods(static pruning or dynamic activation) address this partially,…

Computation and Language · Computer Science 2025-02-27 Yiheng Yang , Yujie Wang , Chi Ma , Lei Yu , Emmanuele Chersoni , Chu-Ren Huang

Active learning is designed to minimize annotation efforts by prioritizing instances that most enhance learning. However, many active learning strategies struggle with a `cold-start' problem, needing substantial initial data to be…

Computation and Language · Computer Science 2026-01-14 Markus Bayer , Justin Lutz , Christian Reuter

Current deep learning based text classification methods are limited by their ability to achieve fast learning and generalization when the data is scarce. We address this problem by integrating a meta-learning procedure that uses the…

The increasing demand for long-context modeling in large language models (LLMs) is bottlenecked by the quadratic complexity of the standard self-attention mechanism. The community has proposed sparse attention to mitigate this issue.…

Artificial Intelligence · Computer Science 2025-11-18 Jingze Shi , Yifan Wu , Yiran Peng , Bingheng Wu , Liangdong Wang , Guang Liu , Yuyu Luo