English
Related papers

Related papers: MARch\'e: Fast Masked Autoregressive Image Generat…

200 papers

Flow-based generative models have shown an excellent ability to explicitly learn the probability density function of data via a sequence of invertible transformations. Yet, learning attentions in generative flows remains understudied, while…

Machine Learning · Computer Science 2022-04-01 Rhea Sanjay Sukthanker , Zhiwu Huang , Suryansh Kumar , Radu Timofte , Luc Van Gool

Retrieval-Augmented Generation (RAG) is often used with Large Language Models (LLMs) to infuse domain knowledge or user-specific information. In RAG, given a user query, a retriever extracts chunks of relevant text from a knowledge base.…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-02-25 Shubham Agarwal , Sai Sundaresan , Subrata Mitra , Debabrata Mahapatra , Archit Gupta , Rounak Sharma , Nirmal Joshua Kapu , Tong Yu , Shiv Saini

This work aims at a challenging task: human action-reaction synthesis, i.e., generating human reactions conditioned on the action sequence of another person. Currently, autoregressive modeling approaches with vector quantization (VQ) have…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Yabiao Wang , Shuo Wang , Jiangning Zhang , Jiafu Wu , Qingdong He , Yong Liu

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

Diffusion models have emerged as a promising approach for generating high-quality, high-dimensional images. Nevertheless, these models are hindered by their high computational cost and slow inference, partly due to the quadratic…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Omid Saghatchian , Atiyeh Gh. Moghadam , Ahmad Nickabadi

We introduce Hybrid Autoregressive Transformer (HART), an autoregressive (AR) visual generation model capable of directly generating 1024x1024 images, rivaling diffusion models in image generation quality. Existing AR models face…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Haotian Tang , Yecheng Wu , Shang Yang , Enze Xie , Junsong Chen , Junyu Chen , Zhuoyang Zhang , Han Cai , Yao Lu , Song Han

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

Memory-augmented Large Language Models (LLMs) have demonstrated remarkable capability for complex and long-horizon embodied planning. By keeping track of past experiences and environmental states, memory enables LLMs to maintain a global…

Robotics · Computer Science 2026-03-18 Zebin Yang , Tong Xie , Baotong Lu , Shaoshan Liu , Bo Yu , Meng Li

Autoregressive sequence modeling stands as the cornerstone of modern Generative AI, powering results across diverse modalities ranging from text generation to image generation. However, a fundamental limitation of this paradigm is the rigid…

Machine Learning · Computer Science 2026-02-02 Yangyan Li

Autoregressive models, often built on Transformer architectures, represent a powerful paradigm for generating ultra-long videos by synthesizing content in sequential chunks. However, this sequential generation process is notoriously slow.…

Computer Vision and Pattern Recognition · Computer Science 2026-02-12 Yuexiao Ma , Xuzhe Zheng , Jing Xu , Xiwei Xu , Feng Ling , Xiawu Zheng , Huafeng Kuang , Huixia Li , Xing Wang , Xuefeng Xiao , Fei Chao , Rongrong Ji

Controllable generative models have been widely used to improve the realism of synthetic visual content. However, such models must handle control conditions and content generation computational requirements, resulting in generally low…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Lin Liu , Huixia Ben , Shuo Wang , Jinda Lu , Junxiang Qiu , Shengeng Tang , Yanbin Hao

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

The quadratic complexity of the attention mechanism and the substantial memory footprint of the Key-Value (KV) cache present severe computational and memory challenges for Large Language Models (LLMs) processing long contexts. Existing…

Machine Learning · Computer Science 2026-03-10 Dongfang Li , Zixuan Liu , Gang Lin , Baotian Hu , Min Zhang

Typical techniques for video captioning follow the encoder-decoder framework, which can only focus on one source video being processed. A potential disadvantage of such design is that it cannot capture the multiple visual context…

Computer Vision and Pattern Recognition · Computer Science 2019-05-13 Wenjie Pei , Jiyuan Zhang , Xiangrong Wang , Lei Ke , Xiaoyong Shen , Yu-Wing Tai

KV cache pruning has emerged as a promising technique for reducing memory and computation costs in long-context auto-regressive generation. Existing methods for vision-language models (VLMs) typically rely on self-attention scores from…

Computer Vision and Pattern Recognition · Computer Science 2024-12-09 Xiaohuan Pei , Tao Huang , Chang Xu

Controllable generation, which enables fine-grained control over generated outputs, has emerged as a critical focus in visual generative models. Currently, there are two primary technical approaches in visual generation: diffusion models…

Computer Vision and Pattern Recognition · Computer Science 2024-10-08 Ziyu Yao , Jialin Li , Yifeng Zhou , Yong Liu , Xi Jiang , Chengjie Wang , Feng Zheng , Yuexian Zou , Lei Li

Long-context inference in large language models (LLMs) is increasingly constrained by the KV cache bottleneck: memory usage grows linearly with sequence length, while attention computation scales quadratically. Existing approaches address…

Computation and Language · Computer Science 2025-11-13 Huanxuan Liao , Yixing Xu , Shizhu He , Guanchen Li , Xuanwu Yin , Dong Li , Emad Barsoum , Jun Zhao , Kang Liu

Autoregressive video diffusion models support real-time synthesis but suffer from error accumulation and context loss over long horizons. We discover that attention heads in AR video diffusion transformers serve functionally distinct roles…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Jiahao Tian , Yiwei Wang , Gang Yu , Chi Zhang

Any-order autoregressive models (AO-ARMs) offer a promising path toward efficient masked diffusion by enabling native key-value caching, but competitive performance has so far required two-stream attention, typically motivated as a means of…

Machine Learning · Computer Science 2026-02-19 Patrick Pynadath , Ruqi Zhang

Recently, autoregressive (AR) language models have emerged as a dominant approach in speech synthesis, offering expressive generation and scalable training. However, conventional AR speech synthesis models relying on the next-token…

Sound · Computer Science 2025-06-30 Bohan Li , Zhihan Li , Haoran Wang , Hanglei Zhang , Yiwei Guo , Hankun Wang , Xie Chen , Kai Yu