English
Related papers

Related papers: Mixture-of-Depths: Dynamically allocating compute …

200 papers

Transformer layers, which use an alternating pattern of multi-head attention and multi-layer perceptron (MLP) layers, provide an effective tool for a variety of machine learning problems. As the transformer layers use residual connections…

Machine Learning · Computer Science 2022-12-13 Yaofeng Desmond Zhong , Tongtao Zhang , Amit Chakraborty , Biswadip Dey

Efficient deployment of a pre-trained LLM to a cluster with multiple servers is a critical step for providing fast responses to users' queries. The recent success of Mixture-of-Experts (MoE) LLMs raises the question of how to deploy them…

Networking and Internet Architecture · Computer Science 2025-08-14 Danil Sivtsov , Aleksandr Katrutsa , Ivan Oseledets

Token representations in high-dimensional latent spaces often exhibit redundancy, limiting computational efficiency and reducing structural coherence across model layers. Hierarchical latent space folding introduces a structured…

Computation and Language · Computer Science 2025-08-11 Fenella Harcourt , Naderdel Piero , Gilbert Sutherland , Daphne Holloway , Harriet Bracknell , Julian Ormsby

Continual learning in environments with shifting data distributions is a challenging problem with several real-world applications. In this paper we consider settings in which the data distribution(task) shifts abruptly and the timing of…

Machine Learning · Computer Science 2022-01-07 Mengda Xu , Sumitra Ganesh , Pranay Pasula

Vision transformers have achieved leading performance on various visual tasks yet still suffer from high computational complexity. The situation deteriorates in dense prediction tasks like semantic segmentation, as high-resolution inputs…

Computer Vision and Pattern Recognition · Computer Science 2023-09-29 Quan Tang , Bowen Zhang , Jiajun Liu , Fagui Liu , Yifan Liu

We propose ADAPT, a meta-learning algorithm that \emph{learns} task sampling proportions under an explicit token budget for multi-task instruction tuning. Instead of fixing task weights by hand, \adapt{} maintains a continuous distribution…

Computation and Language · Computer Science 2025-12-05 Pritam Kadasi , Abhishek Upperwal , Mayank SIngh

The vast majority of natural sensory data is temporally redundant. Video frames or audio samples which are sampled at nearby points in time tend to have similar values. Typically, deep learning algorithms take no advantage of this…

Neural and Evolutionary Computing · Computer Science 2017-06-14 Peter O'Connor , Efstratios Gavves , Max Welling

Long-context efficiency has recently become a trending topic in serving large language models (LLMs). And mixture of depths (MoD) is proposed as a perfect fit to bring down both latency and memory. In this paper, however, we discover that…

Computation and Language · Computer Science 2024-10-21 Chen Zhang , Meizhi Zhong , Qimeng Wang , Xuantao Lu , Zheyu Ye , Chengqiang Lu , Yan Gao , Yao Hu , Kehai Chen , Min Zhang , Dawei Song

Diffusion language models (DLMs) have shown strong potential for general natural language tasks with in-context examples. However, due to the bidirectional attention mechanism, DLMs incur substantial computational cost as context length…

Computation and Language · Computer Science 2026-01-07 Yang Li , Han Meng , Chenan Wang , Haipeng Chen

We show that a constant number of self-attention layers can efficiently simulate, and be simulated by, a constant number of communication rounds of Massively Parallel Computation. As a consequence, we show that logarithmic depth is…

Machine Learning · Computer Science 2024-02-15 Clayton Sanford , Daniel Hsu , Matus Telgarsky

The prevalence of Transformer-based pre-trained language models (PLMs) has led to their wide adoption for various natural language processing tasks. However, their excessive overhead leads to large latency and computational costs. The…

Computation and Language · Computer Science 2023-05-23 Wenxi Tan

Pre-training of Large Language Models is often prohibitively expensive and inefficient at scale, requiring complex and invasive modifications in order to achieve high data throughput. In this work, we present Token-Superposition Training…

Computation and Language · Computer Science 2026-05-20 Bowen Peng , Théo Gigant , Jeffrey Quesnelle

Non-stationary environments are challenging for reinforcement learning algorithms. If the state transition and/or reward functions change based on latent factors, the agent is effectively tasked with optimizing a behavior that maximizes…

Machine Learning · Computer Science 2021-05-21 Lucas N. Alegre , Ana L. C. Bazzan , Bruno C. da Silva

The performance and behavior of large-scale distributed applications is highly influenced by network properties such as latency, bandwidth, packet loss, and jitter. For instance, an engineer might need to answer questions such as: What is…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-04-07 Paulo Gouveia , João Neves , Carlos Segarra , Luca Liechti , Shady Issa , Valerio Schiavoni , Miguel Matos

Large language models (LLMs) have made significant strides in complex tasks, yet their widespread adoption is impeded by substantial computational demands. With hundreds of billion parameters, transformer-based LLMs necessitate months of…

Machine Learning · Computer Science 2024-08-22 Pihe Hu , Shaolong Li , Longbo Huang

Given the limitations of backpropagation, perturbation-based gradient computation methods have recently gained focus for learning with only forward passes, also referred to as queries. Conventional forward learning consumes enormous queries…

Machine Learning · Computer Science 2025-03-11 Tao Ren , Zishi Zhang , Jinyang Jiang , Guanghao Li , Zeliang Zhang , Mingqian Feng , Yijie Peng

Recent studies have shown that diffusion language models achieve remarkable data efficiency under limited-data constraints, yet the underlying mechanisms remain unclear. In this work, we perform extensive ablation experiments to disentangle…

Computation and Language · Computer Science 2025-10-07 Zitian Gao , Haoming Luo , Lynx Chen , Jason Klein Liu , Ran Tao , Joey Zhou , Bryan Dai

Various models have been proposed to incorporate knowledge of syntactic structures into neural language models. However, previous works have relied heavily on elaborate components for a specific language model, usually recurrent neural…

Computation and Language · Computer Science 2022-03-22 Zhixian Yang , Xiaojun Wan

Large Language Models (LLMs) process every token through all layers of a transformer stack, causing wasted computation on simple queries and insufficient flexibility for harder ones that need deeper reasoning. Adaptive-depth methods can…

Computation and Language · Computer Science 2026-05-20 Ahmed Heakl , Martin Gubri , Salman Khan , Sangdoo Yun , Seong Joon Oh

Diffusion Large Language Models (DLLMs) offer a compelling alternative to Auto-Regressive models, but their deployment is constrained by high decoding cost. In this work, we identify a key inefficiency in DLLM decoding: while computation is…

Machine Learning · Computer Science 2026-02-02 Kaihua Liang , Xin Tan , An Zhong , Hong Xu , Marco Canini