English
Related papers

Related papers: Fast-weight Product Key Memory

200 papers

Feed-forward neural networks consist of a sequence of layers, in which each layer performs some processing on the information from the previous layer. A downside to this approach is that each layer (or module, as multiple modules can…

Machine Learning · Computer Science 2020-10-19 Alex Lamb , Anirudh Goyal , Agnieszka Słowik , Michael Mozer , Philippe Beaudoin , Yoshua Bengio

To enable broader deployment of Large Language Models (LLMs), it is essential to identify the best-performing model under strict memory constraints. We present AMQ, Automated Mixed-Precision Weight-Only Quantization, a framework that…

Machine Learning · Computer Science 2025-09-16 Sangjun Lee , Seung-taek Woo , Jungyu Jin , Changhun Lee , Eunhyeok Park

Generative Large Language Models (LLMs) have demonstrated remarkable results for a wide range of tasks. However, deploying these models for inference has been a significant challenge due to their unprecedented resource requirements. This…

Computation and Language · Computer Science 2024-06-06 Sehoon Kim , Coleman Hooper , Amir Gholami , Zhen Dong , Xiuyu Li , Sheng Shen , Michael W. Mahoney , Kurt Keutzer

Large language models (LLMs) show excellent performance but are compute- and memory-intensive. Quantization can reduce memory and accelerate inference. However, existing methods cannot maintain accuracy and hardware efficiency at the same…

Computation and Language · Computer Science 2024-04-03 Guangxuan Xiao , Ji Lin , Mickael Seznec , Hao Wu , Julien Demouth , Song Han

Existing research on task incremental learning in continual learning has primarily focused on preventing catastrophic forgetting (CF). Although several techniques have achieved learning with no CF, they attain it by letting each task…

Machine Learning · Computer Science 2023-06-27 Tatsuya Konishi , Mori Kurokawa , Chihiro Ono , Zixuan Ke , Gyuhak Kim , Bing Liu

Low-frequency terms are a recurring challenge for information retrieval models, especially neural IR frameworks struggle with adequately capturing infrequently observed words. While these terms are often removed from neural models - mainly…

Information Retrieval · Computer Science 2019-05-01 Sebastian Hofstätter , Navid Rekabsaz , Carsten Eickhoff , Allan Hanbury

Mechanistic interpretability aims to reverse-engineer the internal computations of Large Language Models (LLMs), yet separating sparse semantic signals from high-dimensional polysemantic noise remains a significant challenge. This paper…

Quantum Physics · Physics 2026-02-09 Jonathan Pan

Scaling autoregressive large language models (LLMs) has driven unprecedented progress but comes with vast computational costs. In this work, we tackle these costs by leveraging unstructured sparsity within an LLM's feedforward layers, the…

Machine Learning · Computer Science 2026-05-11 Edoardo Cetin , Stefano Peluchetti , Emilio Castillo , Akira Naruse , Mana Murakami , Llion Jones

Leveraging Large Language Models (LLMs) as federated learning (FL)-based time series foundation models offers a promising way to transfer the generalization capabilities of LLMs to time series data while preserving access to private data.…

Machine Learning · Computer Science 2026-04-07 Liwei Deng , Qingxiang Liu , Xinhe Niu , Shengchao Chen , Sheng Sun , Yuankai Wu , Guodong Long , Yuxuan Liang

Long-context question-answering (LCQA) systems have greatly benefited from the powerful reasoning capabilities of large language models (LLMs), which can be categorized into slow and quick reasoning modes. However, both modes have their…

Computation and Language · Computer Science 2025-04-01 Zhengyi Zhao , Shubo Zhang , Zezhong Wang , Bin Liang , Binyang Li , Kam-Fai Wong

Fine-tuning is essential to adapt general-purpose large language models (LLMs) to domain-specific tasks. As a privacy-preserving framework to leverage decentralized data for collaborative model training, Federated Learning (FL) is gaining…

Machine Learning · Computer Science 2026-02-04 Guohao Yang , Tongle Wu , Yuanxiong Guo , Ying Sun , Yanmin Gong

Large language models (LLMs) require substantial compute, and thus energy, at inference time. While quantizing weights and activations is effective at improving efficiency, naive quantization of LLMs can significantly degrade performance…

Machine Learning · Computer Science 2025-06-06 Boris van Breugel , Yelysei Bondarenko , Paul Whatmough , Markus Nagel

Long short-term memory (LSTM) is one of the robust recurrent neural network architectures for learning sequential data. However, it requires considerable computational power to learn and implement both software and hardware aspects. This…

Machine Learning · Computer Science 2023-01-13 Nelly Elsayed , Zag ElSayed , Anthony S. Maida

Fine-tuning pre-trained language models (PLMs) achieves impressive performance on a range of downstream tasks, and their sizes have consequently been getting bigger. Since a different copy of the model is required for each task, this…

Computation and Language · Computer Science 2022-12-01 Ameet Deshpande , Md Arafat Sultan , Anthony Ferritto , Ashwin Kalyan , Karthik Narasimhan , Avirup Sil

The computational and memory demands of vanilla attention scale quadratically with the sequence length $N$, posing significant challenges for processing long sequences in Transformer models. FlashAttention alleviates these challenges by…

Machine Learning · Computer Science 2025-03-04 Guoxia Wang , Jinle Zeng , Xiyuan Xiao , Siming Wu , Jiabin Yang , Lujing Zheng , Zeyu Chen , Jiang Bian , Dianhai Yu , Haifeng Wang

Large Language Models (LLMs) face efficiency bottlenecks due to the quadratic complexity of the attention mechanism when processing long contexts. Sparse attention methods offer a promising solution, but existing approaches often suffer…

Computation and Language · Computer Science 2025-03-06 Lida Chen , Dong Xu , Chenxin An , Xintao Wang , Yikai Zhang , Jiangjie Chen , Zujie Liang , Feng Wei , Jiaqing Liang , Yanghua Xiao , Wei Wang

Large language models (LLMs) have grown beyond the memory capacity of single GPU devices, necessitating quantization techniques for practical deployment. While NF4 (4-bit NormalFloat) quantization enables 4$\times$ memory reduction,…

Machine Learning · Computer Science 2026-04-06 Xiangbo Qi , Chaoyi Jiang , Murali Annavaram

Deploying LLMs on edge devices presents serious technical challenges. Memory elasticity is crucial for edge devices with unified memory, where memory is shared and fluctuates dynamically. Existing solutions suffer from either poor…

Artificial Intelligence · Computer Science 2025-01-14 Yuji Chai , Mujin Kwen , David Brooks , Gu-Yeon Wei

Modern autoregressive models rely on attention, yet the Softmax full attention in Transformers scales quadratically with sequence length. Sliding Window Attention (SWA) achieves linear-time encoding/decoding by constraining the attention…

Machine Learning · Computer Science 2026-01-08 Jiaxu Liu , Yuhe Bai , Xiangyu Yin , Christos-Savvas Bouganis

Large language models (LLMs) exhibit excellent performance in various tasks. However, the memory requirements of LLMs present a great challenge when deploying on memory-limited devices, even for quantized LLMs. This paper introduces a…

Computation and Language · Computer Science 2025-02-24 Weilan Wang , Yu Mao , Dongdong Tang , Hongchao Du , Nan Guan , Chun Jason Xue