English
Related papers

Related papers: When Does Content-Based Routing Work? Representati…

200 papers

Linear State Space Models (SSMs) offer remarkable performance gains in efficient sequence modeling, with constant inference-time computation and memory complexity. Recent advances, such as Mamba, further enhance SSMs with input-dependent…

Machine Learning · Computer Science 2025-06-24 Zheng Zhan , Liliang Ren , Shuohang Wang , Liyuan Liu , Yang Liu , Yeyun Gong , Yanzhi Wang , Yelong Shen

Advancements in deep learning are driven by training models with increasingly larger numbers of parameters, which in turn heightens the computational demands. To address this issue, Mixture-of-Depths (MoD) models have been proposed to…

Computer Vision and Pattern Recognition · Computer Science 2024-12-31 Advait Gadhikar , Souptik Kumar Majumdar , Niclas Popp , Piyapat Saranrittichai , Martin Rapp , Lukas Schott

As AI moves beyond text, large language models (LLMs) increasingly power vision, audio, and document understanding; however, their high inference costs hinder real-time, scalable deployment. Conversely, smaller open-source models offer cost…

Computation and Language · Computer Science 2025-11-11 Mayank Saini , Arit Kumar Bishwas

With the rapid growth of encrypted network traffic, effective traffic classification has become essential for network security and quality of service management. Current machine learning and deep learning approaches for traffic…

Machine Learning · Computer Science 2026-01-30 Tongze Wang , Xiaohui Xie , Wenduo Wang , Chuyi Wang , Jinzhou Liu , Boyan Huang , Yannan Hu , Youjian Zhao , Yong Cui

Mixture-of-Experts (MoE) models improve efficiency through sparse activation, but their learned gating functions provide limited insight into routing decisions. This work introduces the Semantic Resonance Architecture (SRA), which routes…

Computation and Language · Computer Science 2026-04-17 Ivan Ternovtsii , Yurii Bilak

Recent progress in large language models demonstrates that hybrid architectures--combining self-attention mechanisms with structured state space models like Mamba--can achieve a compelling balance between modeling quality and computational…

Computation and Language · Computer Science 2026-04-22 Sangmin Bae , Bilge Acun , Chien-Yu Lin , Haroun Habeeb , Seungyeon Kim , Liang Luo , Junjie Wang , Carole-Jean Wu

Production AI agents frequently receive user-specific queries that are highly repetitive, with up to 47\% being semantically similar to prior interactions, yet each query is typically processed with the same computational cost. We argue…

Computation and Language · Computer Science 2026-03-25 Xunzhuo Liu , Bowei He , Xue Liu , Andy Luo , Haichen Zhang , Huamin Chen

Large language models (LLMs) have advanced significantly due to the attention mechanism, but their quadratic complexity and linear memory demands limit their performance on long-context tasks. Recently, researchers introduced Mamba, an…

Computation and Language · Computer Science 2024-10-22 Wangjie You , Zecheng Tang , Juntao Li , Lili Yao , Min Zhang

U-shaped architectures have long dominated the field of medical image segmentation, while Transformers are widely employed for modeling long-range dependencies. The former typically handles scale variations implicitly by aggregating…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Yanhua Zhang , Ke Zhang , Jingyu Wang , Gabriella Balestra , Samanta Rosati , Yulin Wu , Wuwei Wang , Valentina Giannini

The task of multimodal learning has seen a growing interest recently as it allows for training neural architectures based on different modalities such as vision, text, and audio. One challenge in training such models is that they need to…

Computer Vision and Pattern Recognition · Computer Science 2021-12-03 Kevin Duarte , Brian Chen , Nina Shvetsova , Andrew Rouditchenko , Samuel Thomas , Alexander Liu , David Harwath , James Glass , Hilde Kuehne , Mubarak Shah

The Mamba layer offers an efficient selective state space model (SSM) that is highly effective in modeling multiple domains, including NLP, long-range sequence processing, and computer vision. Selective SSMs are viewed as dual models, in…

Machine Learning · Computer Science 2024-04-02 Ameen Ali , Itamar Zimerman , Lior Wolf

Despite the advantageous subquadratic complexity of modern recurrent deep learning models -- such as state-space models (SSMs) -- recent studies have highlighted their potential shortcomings compared to transformers on reasoning and…

Machine Learning · Computer Science 2025-10-13 Destiny Okpekpe , Antonio Orvieto

Transformers are the cornerstone of modern large language models, but their quadratic computational complexity limits efficiency in long-sequence processing. Recent advancements in Mamba, a state space model (SSM) with linear complexity,…

Machine Learning · Computer Science 2026-01-08 Yixing Li , Ruobing Xie , Zhen Yang , Xingwu Sun , Shuaipeng Li , Weidong Han , Zhanhui Kang , Yu Cheng , Chengzhong Xu , Di Wang , Jie Jiang

Recent advances in large language models highlighted the excessive quadratic cost of self-attention. Despite the significant research efforts, subquadratic attention methods still suffer from inferior performance in practice. We hypothesize…

Machine Learning · Computer Science 2025-05-02 Piotr Piękos , Róbert Csordás , Jürgen Schmidhuber

Text-to-motion generation, which converts motion language descriptions into coherent 3D human motion sequences, has attracted increasing attention in fields, such as avatar animation and humanoid robotic interaction. Though existing models…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Xingzu Zhan , Chen Xie , Honghang Chen , Yixun Lin , Xiaochun Mai

Transformer-based methods have demonstrated remarkable capabilities in 3D semantic segmentation through their powerful attention mechanisms, but the quadratic complexity limits their modeling of long-range dependencies in large-scale point…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Xinyu Wang , Jinghua Hou , Zhe Liu , Yingying Zhu

Mixture-of-Experts (MoE) language models route each token to a small subset of experts, but whether the routes selected by a trained top-$k$ router are good ones is rarely evaluated directly. Holding the model fixed, we compare each…

Machine Learning · Computer Science 2026-05-11 Youngsik Yoon , Siwei Wang , Wei Chen , Jungseul Ok

To answer the question in machine comprehension (MC) task, the models need to establish the interaction between the question and the context. To tackle the problem that the single-pass model cannot reflect on and correct its answer, we…

Computation and Language · Computer Science 2017-04-26 Yichen Gong , Samuel R. Bowman

Token reduction is an effective way to accelerate long-video vision-language models (VLMs), but most existing methods are designed for dense Transformers and do not directly account for hybrid architectures that interleave attention with…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Jindong Jiang , Amala Sanjay Deshmukh , Kateryna Chumachenko , Karan Sapra , Zhiding Yu , Guilin Liu , Andrew Tao , Pavlo Molchanov , Jan Kautz , Wonmin Byeon

Multimodal Large Language Models (MLLMs) struggle with continual learning, often suffering from catastrophic forgetting when adapting to sequential tasks. We introduce a routing-based architecture that integrates new capabilities while…

Machine Learning · Computer Science 2026-04-08 Jay Mohta , Kenan Emir Ak , Gwang Lee , Dimitrios Dimitriadis , Yan Xu , Mingwei Shen