English
Related papers

Related papers: Adaptive Computation Modules: Granular Conditional…

200 papers

Recently, Transformers have gained significant popularity in image restoration tasks such as image super-resolution and denoising, owing to their superior performance. However, balancing performance and computational burden remains a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Leheng Zhang , Wei Long , Yawei Li , Xingyu Zhou , Xiaorui Zhao , Shuhang Gu

Real-world deployment of Vision-Language Models (VLMs) is hindered by high computational demands, as existing architectures inefficiently process all tokens uniformly. We introduce Adaptive Token Pruning (ATP), a dynamic inference mechanism…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Xue Li , Xiaonan Song , Henry Hu

Neural networks in general, from MLPs and CNNs to attention-based Transformers, are constructed from layers of linear combinations followed by nonlinear operations such as ReLU, Sigmoid, or Softmax. Despite their strength, these…

Machine Learning · Computer Science 2025-10-09 Weiguo Lu , Gangnan Yuan , Hong-kun Zhang , Shangyang Li

We introduce a novel architecture and computational framework for formal, automated analysis of systems with a broad set of nonlinearities in the feedback loop, such as neural networks, vision controllers, switched systems, and even simple…

Optimization and Control · Mathematics 2018-05-02 Ivan Papusha , Ufuk Topcu , Steven Carr , Niklas Lauffer

We introduce A-ViT, a method that adaptively adjusts the inference cost of vision transformer (ViT) for images of different complexity. A-ViT achieves this by automatically reducing the number of tokens in vision transformers that are…

Computer Vision and Pattern Recognition · Computer Science 2022-10-10 Hongxu Yin , Arash Vahdat , Jose Alvarez , Arun Mallya , Jan Kautz , Pavlo Molchanov

Modern day Language Models see extensive use in text classification, yet this comes at significant computational cost. Compute-effective classification models are needed for low-resource environments, most notably on edge devices. We…

Machine Learning · Computer Science 2024-11-22 Stan Loosmore , Alexander Titus

Inference-time computation is a powerful paradigm to enhance the performance of large language models (LLMs), with Best-of-N sampling being a widely used technique. However, this method is computationally expensive, requiring both (1) an…

Computation and Language · Computer Science 2024-10-04 Rohin Manvi , Anikait Singh , Stefano Ermon

The collaborative reasoning for understanding each image-question pair is very critical but under-explored for an interpretable Visual Question Answering (VQA) system. Although very recent works also tried the explicit compositional…

Computer Vision and Pattern Recognition · Computer Science 2018-04-03 Qingxing Cao , Xiaodan Liang , Bailing Li , Guanbin Li , Liang Lin

Transformer architecture has become the de-facto model for many machine learning tasks from natural language processing and computer vision. As such, improving its computational efficiency becomes paramount. One of the major computational…

Computation and Language · Computer Science 2022-05-17 Yue Guan , Zhengyi Li , Jingwen Leng , Zhouhan Lin , Minyi Guo

Multimodal deep learning systems are deployed in dynamic scenarios due to the robustness afforded by multiple sensing modalities. Nevertheless, they struggle with varying compute resource availability (due to multi-tenancy, device…

Machine Learning · Computer Science 2025-10-29 Jason Wu , Yuyang Yuan , Kang Yang , Lance Kaplan , Mani Srivastava

The Optimized Gradient Method (OGM), its strongly convex extension, the Information Theoretical Exact Method (ITEM), as well as the related Triple Momentum Method (TMM) have superior convergence guarantees when compared to the Fast Gradient…

Optimization and Control · Mathematics 2024-05-14 Mihai I. Florea

Continual learning is essential for real-world deployment when there is a need to quickly adapt the model to new tasks without forgetting knowledge of old tasks. Existing work on continual sequence generation either always reuses existing…

Computation and Language · Computer Science 2022-04-06 Yanzhe Zhang , Xuezhi Wang , Diyi Yang

We introduce the Block-Recurrent Transformer, which applies a transformer layer in a recurrent fashion along a sequence, and has linear complexity with respect to sequence length. Our recurrent cell operates on blocks of tokens rather than…

Machine Learning · Computer Science 2022-11-03 DeLesley Hutchins , Imanol Schlag , Yuhuai Wu , Ethan Dyer , Behnam Neyshabur

Recently, the attention-enhanced multi-layer encoder, such as Transformer, has been extensively studied in Machine Reading Comprehension (MRC). To predict the answer, it is common practice to employ a predictor to draw information only from…

Computation and Language · Computer Science 2021-02-03 Nuo Chen , Fenglin Liu , Chenyu You , Peilin Zhou , Yuexian Zou

Undirected graphical models are compact representations of joint probability distributions over random variables. To solve inference tasks of interest, graphical models of arbitrary topology can be trained using empirical risk minimization.…

Machine Learning · Computer Science 2020-10-23 Adarsh K. Jeewajee , Leslie P. Kaelbling

Link adaptation, in particular adaptive coded modulation (ACM), is a promising tool for bandwidth-efficient transmission in a fading environment. The main motivation behind employing ACM schemes is to improve the spectral efficiency of…

Information Theory · Computer Science 2016-03-28 Anders Gjendemsjø , Geir E. Øien , Henrik Holm , Mohamed-Slim Alouini , David Gesbert , Kjell J. Hole , Pål Orten

Inexact alternating direction multiplier methods (ADMMs) are developed for solving general separable convex optimization problems with a linear constraint and with an objective that is the sum of smooth and nonsmooth terms. The approach…

Optimization and Control · Mathematics 2016-04-12 William W. Hager , Hongchao Zhang

Audio-visual segmentation (AVS) is an emerging task that aims to accurately segment sounding objects based on audio-visual cues. The success of AVS learning systems depends on the effectiveness of cross-modal interaction. Such a requirement…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Yuanhong Chen , Chong Wang , Yuyuan Liu , Hu Wang , Gustavo Carneiro

Learned Image Compression (LIC) has shown remarkable progress in recent years. Existing works commonly employ CNN-based or self-attention-based modules as transform methods for compression. However, there is no prior research on neural…

Computer Vision and Pattern Recognition · Computer Science 2024-09-25 Yuxi Liu , Wenhan Yang , Huihui Bai , Yunchao Wei , Yao Zhao

The demand for edge AI in vision-language tasks requires models that achieve real-time performance on resource-constrained devices with limited power and memory. This paper proposes two adaptive compression techniques -- Sparse Temporal…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Md Tasnin Tanvir , Soumitra Das , Sk Md Abidar Rahaman , Ali Shiri Sichani