English
Related papers

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

200 papers

Diffusion-based Large Language Models (dLLMs) parallelize text generation by framing decoding as a denoising process, but suffer from high computational overhead since they predict all future suffix tokens at each step while retaining only…

Computation and Language · Computer Science 2025-08-26 Xinhua Chen , Sitao Huang , Cong Guo , Chiyue Wei , Yintao He , Jianyi Zhang , Hai "Helen" Li , Yiran Chen

The key challenge in semantic search is to create models that are both accurate and efficient in pinpointing relevant sentences for queries. While BERT-style bi-encoders excel in efficiency with pre-computed embeddings, they often miss…

Computation and Language · Computer Science 2024-06-26 Zihan Liao , Hang Yu , Jianguo Li , Jun Wang , Wei Zhang

Recent large language models (LLMs) have demonstrated strong reasoning capabilities that benefits from online reinforcement learning (RL). These capabilities have primarily been demonstrated within the left-to-right autoregressive (AR)…

Computation and Language · Computer Science 2025-06-04 Siyan Zhao , Devaansh Gupta , Qinqing Zheng , Aditya Grover

Long input sequences are central to in-context learning, document understanding, and multi-step reasoning of Large Language Models (LLMs). However, the quadratic attention cost of Transformers makes inference memory-intensive and slow.…

Computation and Language · Computer Science 2026-02-19 Rujikorn Charakorn , Edoardo Cetin , Shinnosuke Uesaka , Robert Tjarko Lange

Diffusion large language models (dLLMs) offer a promising paradigm for parallel text generation, but in practice they face an accuracy-parallelism trade-off, where increasing tokens per forward (TPF) often degrades generation quality.…

Computation and Language · Computer Science 2026-05-12 Haoyang Zhou , Li Kong , Shijie Ren , Xiting Wang , Shuang Liang , Guowei Wang , Zhenxuan Pan

Compound AI systems, such as agentic systems, are an emerging trend in large-scale enterprise settings, with multiple LLMs specialized for different users, tasks, and/or roles working together. In these scenarios, different models often…

Diffusion Language Models (DLMs) have recently achieved significant success due to their any-order generation capabilities. However, existing inference methods typically rely on local, immediate-step metrics such as confidence or entropy…

Computation and Language · Computer Science 2025-12-03 Kecheng Chen , Ziru Liu , Xijia Tao , Hui Liu , Xinyu Fu , Suiyun Zhang , Dandan Tu , Lingpeng Kong , Rui Liu , Haoliang Li

Inference-time scaling trades efficiency for increased reasoning accuracy by generating longer or more parallel sequences. However, in Transformer LLMs, generation cost is bottlenecked by the size of the key-value (KV) cache, rather than…

Machine Learning · Computer Science 2025-11-10 Adrian Łańcucki , Konrad Staniszewski , Piotr Nawrot , Edoardo M. Ponti

High throughput serving of large language models (LLMs) requires batching sufficiently many requests at a time. However, existing systems struggle because the key-value cache (KV cache) memory for each request is huge and grows and shrinks…

Machine Learning · Computer Science 2023-09-13 Woosuk Kwon , Zhuohan Li , Siyuan Zhuang , Ying Sheng , Lianmin Zheng , Cody Hao Yu , Joseph E. Gonzalez , Hao Zhang , Ion Stoica

In the field of instruction-following large vision-language models (LVLMs), the efficient deployment of these models faces challenges, notably due to the high memory demands of their key-value (KV) caches. Conventional cache management…

Computer Vision and Pattern Recognition · Computer Science 2024-07-26 Zuyan Liu , Benlin Liu , Jiahui Wang , Yuhao Dong , Guangyi Chen , Yongming Rao , Ranjay Krishna , Jiwen Lu

Auto-regressive models (ARMs) have established a dominant paradigm in language modeling. However, their strictly sequential decoding paradigm imposes fundamental constraints on both inference efficiency and modeling flexibility. To address…

Computation and Language · Computer Science 2026-04-13 Yuyan Zhou , Kai Syun Hou , Weiyu Chen , James Kwok

Diffusion Transformers (DiT) have become the dominant methods in image and video generation yet still suffer substantial computational costs. As an effective approach for DiT acceleration, feature caching methods are designed to cache the…

Machine Learning · Computer Science 2025-11-19 Chang Zou , Evelyn Zhang , Runlin Guo , Haohang Xu , Conghui He , Xuming Hu , Linfeng Zhang

Transformer-based large language models (LLMs) demonstrate impressive potential in various practical applications. However, long context inference poses a significant challenge due to the enormous memory requirements of the key-value (KV)…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-03 Bo Jiang , Taolue Yang , Youyuan Liu , Chengming Zhang , Xubin He , Sian Jin

Diffusion language models (DLMs) have strong theoretical efficiency but are limited by fixed-length decoding and incompatibility with key-value (KV) caches. Block diffusion mitigates these issues, yet still enforces a fixed block size and…

Computation and Language · Computer Science 2025-09-30 Yangzhou Liu , Yue Cao , Hao Li , Gen Luo , Zhe Chen , Weiyun Wang , Xiaobo Liang , Biqing Qi , Lijun Wu , Changyao Tian , Yanting Zhang , Yuqiang Li , Tong Lu , Yu Qiao , Jifeng Dai , Wenhai Wang

Embedding models are a fundamental component of modern AI systems such as semantic search and retrieval-augmented generation. Recent advances in large foundation models have substantially accelerated the development of embedding models,…

Multimedia · Computer Science 2026-02-09 Zihang Wang , Siyue Zhang , Yilun Zhao , Jingyi Yang , Tingyu Song , Anh Tuan Luu , Chen Zhao

Diffusion Large Language Models (dLLMs) represent a new paradigm beyond autoregressive modeling, offering competitive performance while naturally enabling a flexible decoding process. Specifically, dLLMs can generate tokens at arbitrary…

Computation and Language · Computer Science 2026-02-13 Sicheng Feng , Zigeng Chen , Xinyin Ma , Gongfan Fang , Xinchao Wang

Diffusion models have recently gained unprecedented attention in the field of image synthesis due to their remarkable generative capabilities. Notwithstanding their prowess, these models often incur substantial computational costs,…

Computer Vision and Pattern Recognition · Computer Science 2023-12-11 Xinyin Ma , Gongfan Fang , Xinchao Wang

Large Language Model (LLM) serving is increasingly constrained by the growing size of the key-value (KV) cache, which scales with both context length and generation length. Prior work shows that attention is dominated by a small subset of…

Machine Learning · Computer Science 2026-04-21 Nazmul Takbir , Hamidreza Alikhani , Nikil Dutt , Sangeetha Abdu Jyothi

As the use of large language models (LLMs) expands rapidly, so does the range of knowledge needed to supplement various LLM queries. Thus, enabling flexible and efficient injection of new knowledge in LLM inference is critical. Three…

Computation and Language · Computer Science 2024-10-22 Yihua Cheng , Kuntai Du , Jiayi Yao , Junchen Jiang

In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and…

Computation and Language · Computer Science 2024-10-31 Suyu Ge , Yunan Zhang , Liyuan Liu , Minjia Zhang , Jiawei Han , Jianfeng Gao