English
Related papers

Related papers: Locality-aware Parallel Decoding for Efficient Aut…

200 papers

Grounded Conversation Generation (GCG) is an emerging vision-language task that requires models to generate natural language responses seamlessly intertwined with corresponding object segmentation masks. Recent models, such as GLaMM and…

Computer Vision and Pattern Recognition · Computer Science 2025-04-02 Bizhe Bai , Jianjian Cao , Yadan Luo , Tao Chen

We present Visual AutoRegressive modeling (VAR), a new generation paradigm that redefines the autoregressive learning on images as coarse-to-fine "next-scale prediction" or "next-resolution prediction", diverging from the standard…

Computer Vision and Pattern Recognition · Computer Science 2024-06-11 Keyu Tian , Yi Jiang , Zehuan Yuan , Bingyue Peng , Liwei Wang

Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial…

Computer Vision and Pattern Recognition · Computer Science 2022-10-13 Yizeng Han , Zhihang Yuan , Yifan Pu , Chenhao Xue , Shiji Song , Guangyu Sun , Gao Huang

Image anomaly detection and localization perform not only image-level anomaly classification but also locate pixel-level anomaly regions. Recently, it has received much research attention due to its wide application in various fields. This…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Chao Huang , Zhao Kang , Hong Wu

Autoregressive models have demonstrated remarkable success in sequential data generation, particularly in NLP, but their extension to continuous-domain image generation presents significant challenges. Recent work, the masked autoregressive…

Computer Vision and Pattern Recognition · Computer Science 2025-04-28 Tiankai Hang , Jianmin Bao , Fangyun Wei , Dong Chen

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

Auto-regressive models are widely used in sequence generation problems. The output sequence is typically generated in a predetermined order, one discrete unit (pixel or word or character) at a time. The models are trained by teacher-forcing…

Computation and Language · Computer Science 2019-10-23 Daniel Duckworth , Arvind Neelakantan , Ben Goodrich , Lukasz Kaiser , Samy Bengio

The implementation of a vast majority of machine learning (ML) algorithms boils down to solving a numerical optimization problem. In this context, Stochastic Gradient Descent (SGD) methods have long proven to provide good results, both in…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-10-06 Janis Keuper , Franz-Josef Pfreundt

Parallel LLM test-time scaling techniques (e.g., best-of-$N$) require drawing $N>1$ sequences conditioned on the same input prompt. These methods boost accuracy while exploiting the computational efficiency of batching $N$ generations.…

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

Image representation and classification are two fundamental tasks towards multimedia content retrieval and understanding. The idea that shape and texture information (e.g. edge or orientation) are the key features for visual representation…

Computer Vision and Pattern Recognition · Computer Science 2015-08-04 Sheng Guo , Weilin Huang , Yu Qiao

Diffusion models have achieved remarkable progress in high-fidelity image, video, and audio generation, yet inference remains computationally expensive. Nevertheless, current diffusion acceleration methods based on distributed parallelism…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Euisoo Jung , Byunghyun Kim , Hyunjin Kim , Seonghye Cho , Jae-Gil Lee

Ultra-high resolution image segmentation has raised increasing interests in recent years due to its realistic applications. In this paper, we innovate the widely used high-resolution image segmentation pipeline, in which an ultra-high…

Computer Vision and Pattern Recognition · Computer Science 2022-12-07 Wenxi Liu , Qi Li , Xindai Lin , Weixiang Yang , Shengfeng He , Yuanlong Yu

Recent image generation schemes typically capture image distribution in a pre-constructed latent space relying on a frozen image tokenizer. Though the performance of tokenizer plays an essential role to the successful generation, its…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Kai Qiu , Xiang Li , Jason Kuen , Hao Chen , Xiaohao Xu , Jiuxiang Gu , Yinyi Luo , Bhiksha Raj , Zhe Lin , Marios Savvides

Training-free high-resolution (HR) image generation has garnered significant attention due to the high costs of training large diffusion models. Most existing methods begin by reconstructing the overall structure and then proceed to refine…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Yuming Li , Peidong Jia , Daiwei Hong , Yueru Jia , Qi She , Rui Zhao , Ming Lu , Shanghang Zhang

Existing captioning models often adopt the encoder-decoder architecture, where the decoder uses autoregressive decoding to generate captions, such that each token is generated sequentially given the preceding generated tokens. However,…

Computer Vision and Pattern Recognition · Computer Science 2019-06-04 Junlong Gao , Xi Meng , Shiqi Wang , Xia Li , Shanshe Wang , Siwei Ma , Wen Gao

In this work, we design, analyze, and optimize sequential and shared-memory parallel algorithms for partitioned local depths (PaLD). Given a set of data points and pairwise distances, PaLD is a method for identifying strength of pairwise…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-08-01 Aditya Devarakonda , Grey Ballard

Autoregressive models excel in sequential modeling and have proven to be effective for vision-language data. However, the spatial nature of visual signals conflicts with the sequential dependencies of next-token prediction, leading to…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Jiamian Wang , Ziqi Zhou , Chaithanya Kumar Mummadi , Sohail Dianat , Majid Rabbani , Raghuveer Rao , Chen Qiu , Zhiqiang Tao

Linear attention mechanisms have gained prominence in causal language models due to their linear computational complexity and enhanced speed. However, the inherent decay mechanism in linear attention presents challenges when applied to…

Computation and Language · Computer Science 2024-06-03 Zhen Qin , Yuxin Mao , Xuyang Shen , Dong Li , Jing Zhang , Yuchao Dai , Yiran Zhong

Materials synthesis platforms that are designed for autonomous experimentation are capable of collecting multimodal diagnostic data that can be utilized for feedback to optimize material properties. Pulsed laser deposition (PLD) is emerging…

Materials Science · Physics 2024-11-01 Sumner B. Harris , Christopher M. Rouleau , Kai Xiao , Rama K. Vasudevan