English
Related papers

Related papers: ASVD: Activation-aware Singular Value Decompositio…

200 papers

Post-training activation compression is essential for deploying Large Language Models (LLMs) on resource-constrained hardware. However, standard methods like Singular Value Decomposition (SVD) are gradient-blind: they preserve high-variance…

Machine Learning · Computer Science 2026-01-13 Ibne Farabi Shihab , Sanjeda Akter , Anuj Sharma

Vision-language models (VLMs) show remarkable performance in multimodal tasks. However, excessively long multimodal inputs lead to oversized Key-Value (KV) caches, resulting in significant memory consumption and I/O bottlenecks. Previous KV…

Computation and Language · Computer Science 2025-01-28 Zunhai Su , Wang Shen , Linge Li , Zhe Chen , Hanyu Wei , Huangqi Yu , Kehong Yuan

Modern large language models are increasingly deployed under compute and memory constraints, making flexible control of model capacity a central challenge. While sparse and low-rank structures naturally trade off capacity and performance,…

Machine Learning · Computer Science 2026-02-09 Hao Ma , Melis Ilayda Bal , Liang Zhang , Bingcong Li , Niao He , Melanie Zeilinger , Michael Muehlebach

Although large vision-language models (LVLMs) have demonstrated impressive capabilities in multi-modal understanding and reasoning, their practical applications are still limited by massive model parameters and high computational costs.…

Computer Vision and Pattern Recognition · Computer Science 2025-08-01 Ji Ma , Wei Suo , Peng Wang , Yanning Zhang

Efficient real-world deployments of large language models (LLMs) rely on Key-Value (KV) caching for processing and generating long outputs, reducing the need for repetitive computation. For large contexts, Key-Value caches can take up tens…

Training large language models (LLMs) is often constrained by GPU memory limitations. To alleviate memory pressure, activation recomputation and data compression have been proposed as two major strategies. However, both approaches have…

Machine Learning · Computer Science 2025-08-11 Ping Chen , Zhuohong Deng , Ping Li , Shuibing He , Hongzi Zhu , Yi Zheng , Zhefeng Wang , Baoxing Huai , Minyi Guo

While Large Vision-Language Models (LVLMs) demonstrate exceptional multi-modal capabilities, the quadratic computational cost of processing high-resolution visual tokens remains a critical bottleneck. Though recent token reduction…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Surendra Pathak , Bo Han

Large Language Models (LLMs) face a significant bottleneck during autoregressive inference due to the massive memory footprint of the Key-Value (KV) cache. Existing compression techniques like token eviction, quantization, or other low-rank…

Machine Learning · Computer Science 2025-11-25 Santhosh G S , Saurav Prakash , Balaraman Ravindran

Large language models have demonstrated remarkable performance; however, their massive parameter counts make deployment highly expensive. Low-rank approximation offers a promising compression solution, yet existing approaches have two main…

Computation and Language · Computer Science 2026-05-14 Jeffrey T. H. Wong , Cheng Zhang , Xinye Cao , Pedro Gimenes , Christos-Savvas Bouganis , George A. Constantinides , Wayne Luk , Yiren Zhao

This paper proposes a novel communication-efficient Split Learning (SL) framework, named Attention-based Double Compression (ADC), which reduces the communication overhead required for transmitting intermediate Vision Transformers…

Machine Learning · Computer Science 2025-09-19 Federico Alvetreti , Jary Pomponi , Paolo Di Lorenzo , Simone Scardapane

Aligning Large Language Models (LLMs) to cater to different human preferences, learning new skills, and unlearning harmful behavior is an important problem. Search-based methods, such as Best-of-N or Monte-Carlo Tree Search, are performant,…

Machine Learning · Computer Science 2024-05-13 Seungwook Han , Idan Shenfeld , Akash Srivastava , Yoon Kim , Pulkit Agrawal

KV cache eviction has emerged as an effective solution to alleviate resource constraints faced by LLMs in long-context scenarios. However, existing token-level eviction methods often overlook two critical aspects: (1) their irreversible…

Machine Learning · Computer Science 2026-01-21 Yi Zhao , Yajuan Peng , Cam-Tu Nguyen , Zuchao Li , Xiaoliang Wang , Hai Zhao , Xiaoming Fu

Reinforcement learning with verifiable rewards (RLVR) has shown great potential to enhance the reasoning ability of large language models (LLMs). However, due to the limited amount of information provided during the RLVR process, the model…

Computation and Language · Computer Science 2026-02-03 Zhipeng Chen , Xiaobo Qin , Wayne Xin Zhao , Youbin Wu , Ji-Rong Wen

Modern deep neural networks (DNNs) often require high memory consumption and large computational loads. In order to deploy DNN algorithms efficiently on edge or mobile devices, a series of DNN compression algorithms have been explored,…

Machine Learning · Computer Science 2020-04-21 Huanrui Yang , Minxue Tang , Wei Wen , Feng Yan , Daniel Hu , Ang Li , Hai Li , Yiran Chen

Training stability is a persistent challenge in the pre-training of large language models (LLMs), particularly for architectures such as Post-Norm Transformers, which are prone to gradient explosion and dissipation. In this paper, we…

Computation and Language · Computer Science 2025-02-26 Ya Wang , Zhijian Zhuo , Yutao Zeng , Xun Zhou , Jian Yang , Xiaoqing Li

Large Language Models (LLMs) have been widely adopted to process long-context tasks. However, the large memory overhead of the key-value (KV) cache poses significant challenges in long-context scenarios. Existing training-free KV cache…

Machine Learning · Computer Science 2024-10-22 Luning Wang , Shiyao Li , Xuefei Ning , Zhihang Yuan , Shengen Yan , Guohao Dai , Yu Wang

The complexity of state-of-the-art Transformer-based models for skeleton-based action recognition poses significant challenges in terms of computational efficiency and resource utilization. In this paper, we explore the application of…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Soroush Oraki , Harry Zhuang , Jie Liang

Computing eigenvalue decomposition (EVD) of a given linear operator, or finding its leading eigenvalues and eigenfunctions, is a fundamental task in many machine learning and scientific computing problems. For high-dimensional eigenvalue…

Machine Learning · Computer Science 2024-08-22 J. Jon Ryu , Xiangxiang Xu , H. S. Melihcan Erol , Yuheng Bu , Lizhong Zheng , Gregory W. Wornell

The increasing scale and complexity of large language models (LLMs) pose significant inference latency challenges, primarily due to their autoregressive decoding paradigm characterized by the sequential nature of next-token prediction. By…

Computation and Language · Computer Science 2025-08-15 Keyu Chen , Zhifeng Shen , Daohai Yu , Haoqian Wu , Wei Wen , Jianfeng He , Ruizhi Qiao , Xing Sun

Typical large vision-language models (LVLMs) apply autoregressive supervision solely to textual sequences, without fully incorporating the visual modality into the learning process. This results in three key limitations: (1) an inability to…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Dianyi Wang , Wei Song , Yikun Wang , Siyuan Wang , Kaicheng Yu , Zhongyu Wei , Jiaqi Wang