English
Related papers

Related papers: Efficient Beam Search for Large Language Models Us…

200 papers

Supervised hashing aims to map the original features to compact binary codes that are able to preserve label based similarity in the Hamming space. Non-linear hash functions have demonstrated the advantage over linear ones due to their…

Computer Vision and Pattern Recognition · Computer Science 2016-11-17 Guosheng Lin , Chunhua Shen , Qinfeng Shi , Anton van den Hengel , David Suter

Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image. While…

Computer Vision and Pattern Recognition · Computer Science 2022-02-22 Gregor Geigle , Jonas Pfeiffer , Nils Reimers , Ivan Vulić , Iryna Gurevych

This paper proposes a hierarchical attentional neural translation model which focuses on enhancing source-side hierarchical representations by covering both local and global semantic information using a bidirectional tree-based encoder. To…

Computation and Language · Computer Science 2017-07-18 Baosong Yang , Derek F. Wong , Tong Xiao , Lidia S. Chao , Jingbo Zhu

Parameter-efficient tuning aims to mitigate the large memory requirements of adapting pretrained language models for downstream tasks. For example, one popular method, prefix-tuning, prepends trainable tokens to sequences while freezing the…

Computation and Language · Computer Science 2023-05-26 Jonathan Li , Will Aitken , Rohan Bhambhoria , Xiaodan Zhu

Effective attention modules have played a crucial role in the success of Transformer-based large language models (LLMs), but the quadratic time and memory complexities of these attention modules also pose a challenge when processing long…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-06-07 Ao Sun , Weilin Zhao , Xu Han , Cheng Yang , Zhiyuan Liu , Chuan Shi , Maosong Sun

In this paper, we introduce a simple training-free technique to improve the performance of drafter-based speculative decoding (SpD) methods that incorporates language modeling head (LM head) during drafting process. A drafter-based…

Computation and Language · Computer Science 2025-09-30 Raghavv Goel , Sudhanshu Agrawal , Mukul Gagrani , Junyoung Park , Yifan Zao , He Zhang , Tian Liu , Yiping Yang , Xin Yuan , Jiuyan Lu , Chris Lott , Mingu Lee

Existing two-stream models, such as CLIP, encode images and text through independent representations, showing good performance while ensuring retrieval speed, have attracted attention from industry and academia. However, the single…

Computer Vision and Pattern Recognition · Computer Science 2025-02-20 Wanqing Cui , Rui Cheng , Jiafeng Guo , Xueqi Cheng

It has been shown that a class of probabilistic domain models cannot be learned correctly by several existing algorithms which employ a single-link look ahead search. When a multi-link look ahead search is used, the computational complexity…

Artificial Intelligence · Computer Science 2013-02-08 TongSheng Chu , Yang Xiang

FastText has established itself as a fundamental algorithm for learning word representations, demonstrating exceptional capability in handling out-of-vocabulary words through character-level n-gram embeddings. However, its hash-based…

Computation and Language · Computer Science 2025-06-03 Yimin Du

The recent surge of complex attention-based deep learning architectures has led to extraordinary results in various downstream NLP tasks in the English language. However, such research for resource-constrained and morphologically rich…

Computation and Language · Computer Science 2021-02-23 Atharva Kulkarni , Amey Hengle , Rutuja Udyawar

Attention layers are widely used in natural language processing (NLP) and are beginning to influence computer vision architectures. Training very large transformer models allowed significant improvement in both fields, but once trained,…

Machine Learning · Computer Science 2021-05-21 Jean-Baptiste Cordonnier , Andreas Loukas , Martin Jaggi

Although considerable efforts have been devoted to transformer-based ranking models for document search, the relevance-efficiency tradeoff remains a critical problem for ad-hoc ranking. To overcome this challenge, this paper presents BECR…

Information Retrieval · Computer Science 2022-01-07 Yingrui Yang , Yifan Qiao , Jinjin Shao , Mayuresh Anand , Xifeng Yan , Tao Yang

Large reasoning models (LRMs) excel on complex problems but face a critical barrier to efficiency: reinforcement learning (RL) training requires long rollouts for outcome-based rewards, where autoregressive decoding dominates time and…

Machine Learning · Computer Science 2026-02-20 Zeliang Zhang , Xiaodong Liu , Hao Cheng , Hao Sun , Chenliang Xu , Jianfeng Gao

The size of the key-value (KV) cache plays a critical role in determining both the maximum context length and the number of concurrent requests supported during inference in modern language models. The KV cache size grows proportionally…

Computation and Language · Computer Science 2024-09-24 Shashank Rajput , Ying Sheng , Sean Owen , Vitaliy Chiley

Offline handwritten text recognition from images is an important problem for enterprises attempting to digitize large volumes of handmarked scanned documents/reports. Deep recurrent models such as Multi-dimensional LSTMs have been shown to…

Computation and Language · Computer Science 2018-07-27 Arindam Chowdhury , Lovekesh Vig

We introduce a method for efficient multi-label text classification with large language models (LLMs), built on reformulating classification tasks as sequences of dichotomic (yes/no) decisions. Instead of generating all labels in a single…

Computation and Language · Computer Science 2025-11-07 Mikołaj Langner , Jan Eliasz , Ewa Rudnicka , Jan Kocoń

Context-aware Machine Translation aims to improve translations of sentences by incorporating surrounding sentences as context. Towards this task, two main architectures have been applied, namely single-encoder (based on concatenation) and…

Computation and Language · Computer Science 2024-02-05 Paweł Mąka , Yusuf Can Semerci , Jan Scholtes , Gerasimos Spanakis

Sequence-to-Sequence (seq2seq) modeling has rapidly become an important general-purpose NLP tool that has proven effective for many text-generation and sequence-labeling tasks. Seq2seq builds on deep neural language modeling and inherits…

Computation and Language · Computer Science 2016-11-11 Sam Wiseman , Alexander M. Rush

Language models can be viewed as functions that embed text into Euclidean space, where the quality of the embedding vectors directly determines model performance, training such neural networks involves various uncertainties. This paper…

Computation and Language · Computer Science 2025-03-31 Yifei Duan , Raphael Shang , Deng Liang , Yongqiang Cai

Recently proposed speech recognition systems are designed to predict using representations generated by their top layers, employing greedy decoding which isolates each timestep from the rest of the sequence. Aiming for improved performance,…

Computation and Language · Computer Science 2022-04-06 Tomer Wullach , Shlomo E. Chazan