English
Related papers

Related papers: A2SF: Accumulative Attention Scoring with Forgetti…

200 papers

This work studies how to adaptively recompute key-value (KV) caches for diffusion large language models (DLMs) to maximize prediction accuracy while minimizing decoding latency. Prior methods' decoders recompute QKV for all tokens at every…

Computation and Language · Computer Science 2025-12-30 Quan Nguyen-Tri , Mukul Ranjan , Zhiqiang Shen

The attention mechanism is a fundamental component of the Transformer model, contributing to interactions among distinct tokens, in contrast to earlier feed-forward neural networks. In general, the attention scores are determined simply by…

Computation and Language · Computer Science 2024-10-11 Chuanyang Zheng , Yihang Gao , Han Shi , Jing Xiong , Jiankai Sun , Jingyao Li , Minbin Huang , Xiaozhe Ren , Michael Ng , Xin Jiang , Zhenguo Li , Yu Li

Large language models have revolutionized data processing in numerous domains, with their ability to handle extended context reasoning receiving notable recognition. To speed up inference, maintaining a key-value (KV) cache memory is…

Computation and Language · Computer Science 2024-10-22 Zhen Yang , J. N. Han , Kan Wu , Ruobing Xie , An Wang , Xingwu Sun , Zhanhui Kang

As long-context language modeling becomes increasingly important, the cost of maintaining and attending to large Key/Value (KV) caches grows rapidly, becoming a major bottleneck in both training and inference. While prior works such as…

Machine Learning · Computer Science 2026-03-25 Dong Liu , Yanxuan Yu , Ben Lengerich , Ying Nian Wu

Traditional KV cache eviction strategies, which discard less critical KV-pairs based on attention scores, often degrade generation quality, causing context loss or hallucinations. Recent efforts shift toward KV merging, merging eviction…

Computation and Language · Computer Science 2025-11-14 Kunxi Li , Yufan Xiong , Zhonghua Jiang , Yiyun Zhou , Zhaode Wang , Chengfei Lv , Shengyu Zhang

Given a sequence of tokens generated by a language model, we may want to identify the preceding tokens that influence the model to generate this sequence. Performing such token attribution is expensive; a common approach is to ablate…

Machine Learning · Computer Science 2025-04-21 Benjamin Cohen-Wang , Yung-Sung Chuang , Aleksander Madry

As large language models (LLMs) continue to support increasingly longer contexts, the memory demand for key-value (KV) caches during decoding grows rapidly, becoming a critical bottleneck in both GPU memory capacity and PCIe bandwidth.…

Machine Learning · Computer Science 2025-06-23 Feiyu Yao , Qian Wang

Vision-language models (VLMs) typically encode substantially more visual tokens than text tokens, resulting in significant token redundancy. Pruning uninformative visual tokens is therefore crucial for improving computational efficiency,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-19 Kai Zhao , Wubang Yuan , Yuchen Lin , Liting Ruan , Xiaofeng Lu , Deng-Ping Fan , Ming-Ming Cheng , Dan Zeng

Interacting with humans through multi-turn conversations is a fundamental feature of large language models (LLMs). However, existing LLM serving engines executing multi-turn conversations are inefficient due to the need to repeatedly…

Computation and Language · Computer Science 2024-07-02 Bin Gao , Zhuomin He , Puru Sharma , Qingxuan Kang , Djordje Jevdjic , Junbo Deng , Xingkun Yang , Zhou Yu , Pengfei Zuo

Autoregressive Transformer KV caches grow linearly with context length; sliding-window caching bounds memory but discards evicted tokens entirely, so relevant evidence outside the window becomes inaccessible. We introduce \emph{Tensor…

Machine Learning · Computer Science 2026-05-25 Kabir Swain , Sijie Han , Daniel Karl I. Weidele , Mauro Martino , Antonio Torralba

Recent advances in large language models (LLMs) have showcased exceptional performance in long-context tasks, while facing significant inference efficiency challenges with limited GPU memory. Existing solutions first proposed the…

Computation and Language · Computer Science 2025-02-20 Qingfa Xiao , Jiachuan Wang , Haoyang Li , Cheng Deng , Jiaqi Tang , Shuangyin Li , Yongqi Zhang , Jun Wang , Lei Chen

The recently proposed Forgetting Transformer (FoX) incorporates a forget gate into softmax attention and has shown consistently better or on-par performance compared to the standard RoPE-based Transformer. Notably, many attention heads in…

Machine Learning · Computer Science 2025-08-13 Zhixuan Lin , Johan Obando-Ceron , Xu Owen He , Aaron Courville

Large language models (LLMs) utilize key-value (KV) cache to store historical information during sequence processing. The size of KV cache grows linearly as the length of the sequence extends, which seriously affects memory usage and…

Computation and Language · Computer Science 2026-01-16 Yijun Liu , Yixuan Wang , Yuzhuang Xu , Shiyu Ji , Yang Xu , Qingfu Zhu , Wanxiang Che

Neural language models predict the next token using a latent representation of the immediate token history. Recently, various methods for augmenting neural language models with an attention mechanism over a differentiable memory have been…

Computation and Language · Computer Science 2017-02-16 Michał Daniluk , Tim Rocktäschel , Johannes Welbl , Sebastian Riedel

Efficient attention mechanisms enable long-context transformers but often miss globally important tokens, degrading modeling quality. We introduce a pre-scoring framework that assigns a query-independent global importance prior to keys…

Machine Learning · Computer Science 2026-02-10 Zhexiang Li , Haoyu Wang , Yutong Bao , David Woodruff

Multimodal large language models (MLLMs) enhance their perceptual capabilities by integrating visual and textual information. However, processing the massive number of visual tokens incurs a significant computational cost. Existing analysis…

Computer Vision and Pattern Recognition · Computer Science 2024-12-31 Jiedong Zhuang , Lu Lu , Ming Dai , Rui Hu , Jian Chen , Qiang Liu , Haoji Hu

As large language models scale to longer contexts, loading the growing KV cache during attention computation becomes a critical bottleneck. Previous work has shown that attention computation is dominated by a small subset of tokens. This…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-13 Di Liu , Ruitian Wang , Chen Chen , Mingliang Gong , Yongjie Yuan , Han Zhao , Yu Feng , Quan Chen , Minyi Guo

Autoregressive (AR) visual generation has achieved remarkable performance but suffers from high memory usage and low throughput, as it requires caching previously generated visual tokens. Recent research has shown that retaining only a few…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Guotao Liang , Baoquan Zhang , Zhiyuan Wen , Yunming Ye

Attention-based encoder-decoder, e.g. transformer and its variants, generates the output sequence in an autoregressive (AR) manner. Despite its superior performance, AR model is computationally inefficient as its generation requires as many…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-27 Keyu An , Zerui Li , Zhifu Gao , Shiliang Zhang

The quadratic complexity of self-attention in Transformer models remains a significant bottleneck for processing long sequences and deploying large language models efficiently. For this approach, there has been significant research into…

Computation and Language · Computer Science 2026-05-26 Spandan Pratyush
‹ Prev 1 4 5 6 7 8 10 Next ›