English
Related papers

Related papers: Studying the Soupability of Documents in State Spa…

200 papers

The recent advance in neural network architecture and training algorithms have shown the effectiveness of representation learning. The neural network-based models generate better representation than the traditional ones. They have the…

Computation and Language · Computer Science 2018-05-29 Kamal Al-Sabahi , Zhang Zuping , Mohammed Nadher

Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as linear attention,…

Machine Learning · Computer Science 2024-06-03 Albert Gu , Tri Dao

There has been a significant effort by the research community to address the problem of providing methods to organize documentation with the help of information Retrieval methods. In this report paper, we present several experiments with…

Information Retrieval · Computer Science 2022-06-07 Rui Portocarrero Sarmento , Douglas O. Cardoso , João Gama , Pavel Brazdil

Hybrid models that combine state space models (SSMs) with attention mechanisms have shown strong performance by leveraging the efficiency of SSMs and the high recall ability of attention. However, the architectural design choices behind…

Computation and Language · Computer Science 2025-11-03 Hyunji Lee , Wenhao Yu , Hongming Zhang , Kaixin Ma , Jiyeon Kim , Dong Yu , Minjoon Seo

Structured, procedural reasoning is essential for Large Language Models (LLMs), especially in mathematics. While post-training methods have improved LLM performance, they still fall short in capturing deep procedural logic on complex tasks.…

Artificial Intelligence · Computer Science 2025-08-27 Zhichao Yang , Zhaoxin Fan , Gen Li , Yuanze Hu , Xinyu Wang , Ye Qiu , Xin Wang , Yifan Sun , Wenjun Wu

Word embeddings improve the performance of NLP systems by revealing the hidden structural relationships between words. Despite their success in many applications, word embeddings have seen very little use in computational social science NLP…

Computation and Language · Computer Science 2018-02-21 James Foulds

Reasoning-centric large language models (LLMs) achieve strong performance by generating intermediate reasoning trajectories, but often incur excessive token usage and high inference-time decoding cost. We observe that, when solving the same…

Artificial Intelligence · Computer Science 2026-05-12 Han Yang , Mingyan Wu , Bailan He , Zeyu Cao , Sikuan Yan , Kevin Qinghong Lin , Zifeng Ding

We present a novel approach for training small language models for reasoning-intensive document ranking that combines knowledge distillation with reinforcement learning optimization. While existing methods often rely on expensive human…

Information Retrieval · Computer Science 2025-07-01 Chris Samarinas , Hamed Zamani

Data scarcity and class imbalance are persistent challenges in training robust NLP models, especially in specialized domains or low-resource settings. We propose a novel technique, SMOTExT, that adapts the idea of Synthetic Minority…

Computation and Language · Computer Science 2025-05-20 Mateusz Bystroński , Mikołaj Hołysz , Grzegorz Piotrowski , Nitesh V. Chawla , Tomasz Kajdanowicz

The traditional RAG paradigm, which typically engages in the comprehension of relevant text chunks in response to received queries, inherently restricts both the depth of knowledge internalization and reasoning capabilities. To address this…

Computation and Language · Computer Science 2025-10-17 Jihao Zhao , Zhiyuan Ji , Simin Niu , Hanyu Wang , Feiyu Xiong , Zhiyu Li

Models such as latent semantic analysis and those based on neural embeddings learn distributed representations of text, and match the query against the document in the latent semantic space. In traditional information retrieval models, on…

Information Retrieval · Computer Science 2016-10-27 Bhaskar Mitra , Fernando Diaz , Nick Craswell

We explore using multilingual document embeddings for nearest neighbor mining of parallel data. Three document-level representations are investigated: (i) document embeddings generated by simply averaging multilingual sentence embeddings;…

Computation and Language · Computer Science 2019-07-02 Mandy Guo , Yinfei Yang , Keith Stevens , Daniel Cer , Heming Ge , Yun-Hsuan Sung , Brian Strope , Ray Kurzweil

Reasoning models have achieved remarkable performance on tasks like math and logical reasoning thanks to their ability to search during reasoning. However, they still suffer from overthinking, often performing unnecessary reasoning steps…

Artificial Intelligence · Computer Science 2025-04-09 Anqi Zhang , Yulin Chen , Jane Pan , Chen Zhao , Aurojit Panda , Jinyang Li , He He

Selective State Space Models (SSMs), notably Mamba, employ diagonal state transitions that limit both memory retention and bilinear computational capacity. We propose a factorized bilinear input modulation that augments the SSM with a…

Systems and Control · Electrical Eng. & Systems 2026-04-28 Hiroki Fujii , Masaki Yamakita

While model serving has unlocked unprecedented capabilities, the high cost of serving large-scale models continues to be a significant barrier to widespread accessibility and rapid innovation. Compiler optimizations have long driven…

Machine Learning · Computer Science 2026-02-05 Annabelle Sujun Tang , Christopher Priebe , Rohan Mahapatra , Lianhui Qin , Hadi Esmaeilzadeh

Multi-hop question answering is a challenging task with distinct industrial relevance, and Retrieval-Augmented Generation (RAG) methods based on large language models (LLMs) have become a popular approach to tackle this task. Owing to the…

Computation and Language · Computer Science 2025-01-31 Zhouyu Jiang , Mengshu Sun , Lei Liang , Zhiqiang Zhang

The integration of multi-document pre-training objectives into language models has resulted in remarkable improvements in multi-document downstream tasks. In this work, we propose extending this idea by pre-training a generic multi-document…

Computation and Language · Computer Science 2023-05-25 Avi Caciularu , Matthew E. Peters , Jacob Goldberger , Ido Dagan , Arman Cohan

Multimodal large language models (MLLMs) achieve strong performance by jointly processing inputs from multiple modalities, such as vision, audio, and language. However, building such models or extending them to new modalities often requires…

Machine Learning · Computer Science 2026-03-24 Md Kaykobad Reza , Ameya Patil , Edward Ayrapetian , M. Salman Asif

State space models (SSMs) have emerged as an efficient alternative to Transformer models for language modeling, offering linear computational complexity and constant memory usage as context length increases. However, despite their…

Computation and Language · Computer Science 2025-04-23 Zhifan Ye , Kejing Xia , Yonggan Fu , Xin Dong , Jihoon Hong , Xiangchi Yuan , Shizhe Diao , Jan Kautz , Pavlo Molchanov , Yingyan Celine Lin

Selective State-Space Models (SSMs) such as Mamba have emerged as an alternative architecture to self-attention based transformers in sequence modeling tasks. Recent works have demonstrated the use of transformers in some filtering and…

Systems and Control · Electrical Eng. & Systems 2026-04-28 Alex Tang , M. Emrullah Ildiz , Batin Kurt , Samet Oymak , Necmiye Ozay