English
Related papers

Related papers: Decoding in Geometry: Alleviating Embedding-Space …

200 papers

We generalize the leverage score sampling sketch for $\ell_2$-subspace embeddings, to accommodate sampling subsets of the transformed data, so that the sketching approach is appropriate for distributed settings. This is then used to derive…

Information Theory · Computer Science 2024-06-27 Neophytos Charalambides , Mert Pilanci , Alfred Hero

Arithmetic coding is an essential class of coding techniques. One key issue of arithmetic encoding method is to predict the probability of the current coding symbol from its context, i.e., the preceding encoded symbols, which usually can be…

Computer Vision and Pattern Recognition · Computer Science 2018-07-04 Mu Li , Shuhang Gu , David Zhang , Wangmeng Zuo

The growing demand for large language models (LLMs) with tunable reasoning capabilities in many real-world applications highlights a critical need for methods that can efficiently produce a spectrum of models balancing reasoning depth and…

Artificial Intelligence · Computer Science 2025-09-30 Xiaochong Lan , Yu Zheng , Shiteng Cao , Yong Li

Decoding strategies for generative large language models (LLMs) are a critical but often underexplored aspect of text generation tasks. Guided by specific hyperparameters, these strategies aim to transform the raw probability distributions…

Computation and Language · Computer Science 2024-12-17 Esteban Garces Arias , Meimingwei Li , Christian Heumann , Matthias Aßenmacher

Large language models solve complex tasks by generating long reasoning chains, achieving higher accuracy at the cost of increased computational cost and reduced ability to isolate functionally relevant reasoning. Prior work on compact…

Computation and Language · Computer Science 2026-04-22 Janvijay Singh , Dilek Hakkani-Tür

Sampling-based decoding strategies have been widely adopted for Large Language Models (LLMs) in numerous applications, targeting a balance between diversity and quality via temperature tuning and tail truncation. Considering the strong…

Computation and Language · Computer Science 2025-01-09 Yuxuan Zhou , Margret Keuper , Mario Fritz

We address the problem of crowd localization, i.e., the prediction of dots corresponding to people in a crowded scene. Due to various challenges, a localization method is prone to spatial semantic errors, i.e., predicting multiple dots…

Computer Vision and Pattern Recognition · Computer Science 2020-12-24 Shahira Abousamra , Minh Hoai , Dimitris Samaras , Chao Chen

Representing graph data in a low-dimensional space for subsequent tasks is the purpose of attributed graph embedding. Most existing neural network approaches learn latent representations by minimizing reconstruction errors. Rare work…

Machine Learning · Computer Science 2024-01-15 Bozhen Hu , Zelin Zang , Jun Xia , Lirong Wu , Cheng Tan , Stan Z. Li

The sum-rank metric generalizes the Hamming and rank metric by partitioning vectors into blocks and defining the total weight as the sum of the rank weights of these blocks, based on their matrix representation. In this work, we explore…

Information Theory · Computer Science 2024-10-22 Thomas Jerkovits , Hannes Bartz , Antonia Wachter-Zeh

Sampling methods (e.g., node-wise, layer-wise, or subgraph) has become an indispensable strategy to speed up training large-scale Graph Neural Networks (GNNs). However, existing sampling methods are mostly based on the graph structural…

Machine Learning · Computer Science 2021-09-07 Weilin Cong , Rana Forsati , Mahmut Kandemir , Mehrdad Mahdavi

Speculative decoding accelerates large language model inference by proposing tokens with a lightweight draft model and selectively accepting them using a target model. This work introduces DropMatch, a novel approach that matches draft…

Computation and Language · Computer Science 2026-03-05 Jeongtae Lee , Minjung Jo , Hyunjoon Jeong , Gunho Park , Sunghyeon Woo , Joonghoon Kim , Se Jung Kwon , Dongsoo Lee

Decoding methods for large language models often trade-off between diversity of outputs and parallelism of computation. Methods such as beam search and Gumbel top-k sampling can guarantee a different output for each element of the beam, but…

Computation and Language · Computer Science 2023-06-02 Luke Vilnis , Yury Zemlyanskiy , Patrick Murray , Alexandre Passos , Sumit Sanghai

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Machine Learning · Statistics 2026-03-18 Nuri Mert Vural , Alberto Bietti , Mahdi Soltanolkotabi , Denny Wu

A major hurdle in machine learning is scalability to massive datasets. Approaches to overcome this hurdle include compression of the data matrix and distributing the computations. \textit{Leverage score sampling} provides a compressed…

Information Theory · Computer Science 2020-09-16 Neophytos Charalambides , Mert Pilanci , Alfred O. Hero

Decoding sits between a language model and everything we do with it, yet it is still treated as a heuristic knob-tuning exercise. We argue decoding should be understood as a principled optimisation layer: at each token, we solve a…

Machine Learning · Computer Science 2026-02-26 Xiaotong Ji , Rasul Tutunov , Matthieu Zimmer , Haitham Bou-Ammar

This paper develops a theory of clustering and coding which combines a geometric model with a probabilistic model in a principled way. The geometric model is a Riemannian manifold with a Riemannian metric, ${g}_{ij}({\bf x})$, which we…

Machine Learning · Computer Science 2024-05-14 L. Thorne McCarty

Numerical interactions leading to users sharing textual content published by others are naturally represented by a network where the individuals are associated with the nodes and the exchanged texts with the edges. To understand those…

Machine Learning · Computer Science 2024-02-14 Rémi Boutin , Pierre Latouche , Charles Bouveyron

Crowd counting based on density maps is generally regarded as a regression task.Deep learning is used to learn the mapping between image content and crowd density distribution. Although great success has been achieved, some pedestrians far…

Computer Vision and Pattern Recognition · Computer Science 2022-04-18 Jiwei Chen , Kewei Wang , Wen Su , Zengfu Wang

Recently, scaling test-time compute on Large Language Models (LLM) has garnered wide attention. However, there has been limited investigation of how various reasoning prompting strategies perform as scaling. In this paper, we focus on a…

Artificial Intelligence · Computer Science 2025-08-18 Yexiang Liu , Zekun Li , Zhi Fang , Nan Xu , Ran He , Tieniu Tan

We propose a principled method for autoencoding with random forests. Our strategy builds on foundational results from nonparametric statistics and spectral graph theory to learn a low-dimensional embedding of the model that optimally…

Machine Learning · Statistics 2026-01-16 Binh Duc Vu , Jan Kapar , Marvin Wright , David S. Watson