English
Related papers

Related papers: d$^2$Cache: Accelerating Diffusion-Based LLMs via …

200 papers

Large language models (LLMs) excel at capturing global token dependencies via self-attention but face prohibitive compute and memory costs on lengthy inputs. While sub-quadratic methods (e.g., linear attention) can reduce these costs, they…

Machine Learning · Computer Science 2025-06-18 Yeonju Ro , Zhenyu Zhang , Souvik Kundu , Zhangyang Wang , Aditya Akella

Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks, including document processing and code generation. Autoregressive Language Models (ARMs), which generate…

Diffusion Transformers (DiT) are powerful generative models but remain computationally intensive due to their iterative structure and deep transformer stacks. To alleviate this inefficiency, we propose \textbf{FastCache}, a…

Machine Learning · Computer Science 2026-03-30 Dong Liu , Yanxuan Yu , Jiayi Zhang , Yifan Li , Ben Lengerich , Ying Nian Wu

Large language models (LLMs) demonstrate remarkable capabilities but face substantial serving costs due to their high memory demands, with the key-value (KV) cache being a primary bottleneck. State-of-the-art KV cache compression…

Machine Learning · Computer Science 2025-09-03 Yanqi Zhang , Yuwei Hu , Runyuan Zhao , John C. S. Lui , Haibo Chen

Diffusion models have emerged as state-of-the-art in image generation, but their practical deployment is hindered by the significant computational cost of their iterative denoising process. While existing caching techniques can accelerate…

Computer Vision and Pattern Recognition · Computer Science 2025-11-06 Mingyu Sung , Il-Min Kim , Sangseok Yun , Jae-Mo Kang

Recently, sharing key-value (KV) cache across layers has been found effective in efficient inference of large language models (LLMs). To systematically investigate different techniques of cross-layer KV sharing, we propose a unified…

Computation and Language · Computer Science 2025-02-06 You Wu , Haoyi Wu , Kewei Tu

The generation speed of LLMs are bottlenecked by autoregressive decoding, where tokens are predicted sequentially one by one. Alternatively, diffusion large language models (dLLMs) theoretically allow for parallel token generation, but in…

Computation and Language · Computer Science 2025-11-03 Daniel Israel , Guy Van den Broeck , Aditya Grover

Autoregressive large language models achieve strong results on many benchmarks, but decoding remains fundamentally latency-limited by sequential dependence on previously generated tokens. Diffusion language models (DLMs) promise parallel…

Computation and Language · Computer Science 2026-01-06 Yihao Liang , Ze Wang , Hao Chen , Ximeng Sun , Jialian Wu , Xiaodong Yu , Jiang Liu , Emad Barsoum , Zicheng Liu , Niraj K. Jha

Diffusion large language models (dLLMs) represent a significant advancement in text generation, offering parallel token decoding capabilities. However, existing open-source implementations suffer from quality-speed trade-offs that impede…

Computation and Language · Computer Science 2025-10-09 Fanheng Kong , Jingyuan Zhang , Yahui Liu , Zirui Wu , Yu Tian , Victoria W. , Guorui Zhou

As Large Language Models (LLMs) broaden their capabilities to manage thousands of API calls, they are confronted with complex data operations across vast datasets with significant overhead to the underlying system. In this work, we…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-09-24 Simranjit Singh , Michael Fore , Andreas Karatzas , Chaehong Lee , Yanan Jian , Longfei Shangguan , Fuxun Yu , Iraklis Anagnostopoulos , Dimitrios Stamoulis

Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm. By generating tokens in parallel through an iterative denoising process, DLMs possess inherent…

Computation and Language · Computer Science 2025-12-08 Tianyi Li , Mingda Chen , Bowei Guo , Zhiqiang Shen

Diffusion language models (DLMs) generate text through iterative denoising, but inference requires full-sequence attention at every iteration, resulting in substantial redundant computation on masked tokens. Block-wise diffusion can reduce…

Machine Learning · Computer Science 2026-02-03 Fengrui Zuo , Zhiwei Ke , Yiming Liu , Wenqi Lou , Chao Wang , Xuehai Zhou

Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) generation, yet their reliance on Transformer backbones limits inference efficiency due to quadratic attention or KV-cache overhead. We…

Machine Learning · Computer Science 2026-03-02 Vaibhav Singh , Oleksiy Ostapenko , Pierre-André Noël , Eugene Belilovsky , Torsten Scholak

Recent advancements in large language models (LLMs) have significantly improved Natural Language to SQL (NL2SQL) tasks, yet most NL2SQL systems continue to rely on the autoregressive (AR) paradigm. The highly structured nature of SQL makes…

Databases · Computer Science 2026-05-28 Peixian Ma , Xialie Zhuang , Jiantao Tan , Changlun Li , Ruirui Chen , Chengwei Qin

Diffusion large language models (dLLMs) are emerging as a promising alternative to autoregressive models (ARMs) due to their ability to capture bidirectional context and the potential for parallel generation. Despite the advantages, dLLM…

Machine Learning · Computer Science 2026-03-12 Zijian Zhu , Fei Ren , Zhanhong Tan , Kaisheng Ma

Recent advances in large language models (LLMs) have inspired new paradigms for document reranking. While this paradigm better exploits the reasoning and contextual understanding capabilities of LLMs, most existing LLM-based rerankers rely…

Information Retrieval · Computer Science 2026-02-16 Qi Liu , Kun Ai , Jiaxin Mao , Yanzhao Zhang , Mingxin Li , Dingkun Long , Pengjun Xie , Fengbin Zhu , Ji-Rong Wen

Diffusion language models (DLMs) provide a bidirectional generation framework naturally suited for infilling, yet their performance is constrained by the pre-specified infilling length. In this paper, we reveal that DLMs possess an inherent…

Machine Learning · Computer Science 2026-02-03 Hengchang Liu , Zhao Yang , Bing Su

Diffusion-based decoding has recently emerged as an appealing alternative to autoregressive (AR) generation, offering the potential to update multiple tokens in parallel and reduce latency. However, diffusion vision language models (dVLMs)…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Lunbin Zeng , Jingfeng Yao , Bencheng Liao , Hongyuan Tao , Wenyu Liu , Xinggang Wang

Large Language Models (LLMs) have become the new foundation for many applications, reshaping human society like a storm. Disaggregated inference, which separates prefill and decode stages, is a promising approach to improving hardware…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-01-28 Shiyang Chen , Rain Jiang , Dezhi Yu , Jinlai Xu , Mengyuan Chao , Fanlong Meng , Chenyu Jiang , Wei Xu , Hang Liu

The deployment of large language models (LLMs) is often hindered by the extensive memory requirements of the Key-Value (KV) cache, especially as context lengths increase. Existing approaches to reduce the KV cache size involve either…

Computation and Language · Computer Science 2024-11-05 Alessio Devoto , Yu Zhao , Simone Scardapane , Pasquale Minervini