# Papers, Page 12 of 12 Source: https://savrn.com/papers/page/12 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- SAVRN Model Hub # Research Papers The research behind the models: full abstracts, authors, publication dates, and every model in the library that cites each paper. 11,122Models 3,164Datasets 285Papers 6,792Publishers 11,852Sourced relationships Updated 2026-10-18 · [How the library is built](https://savrn.com/model-hub/methodology) ## Filter Papers Published - [202630](https://savrn.com/papers?year=2026) - [202536](https://savrn.com/papers?year=2025) - [202438](https://savrn.com/papers?year=2024) - [202339](https://savrn.com/papers?year=2023) - [202229](https://savrn.com/papers?year=2022) - [202142](https://savrn.com/papers?year=2021) - [202021](https://savrn.com/papers?year=2020) - [201929](https://savrn.com/papers?year=2019) - [201812](https://savrn.com/papers?year=2018) - [20176](https://savrn.com/papers?year=2017) - [20161](https://savrn.com/papers?year=2016) - [20151](https://savrn.com/papers?year=2015) - [20121](https://savrn.com/papers?year=2012) [Most recent](https://savrn.com/papers?sort=published)[Name](https://savrn.com/papers?sort=name) 285 papers, sorted by most recent. Paper ### [ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension](https://savrn.com/papers/record-bridging-the-gap-between-human-and-machine-commonsense-reading-comprehension) We present a large-scale dataset, ReCoRD, for machine reading comprehension requiring commonsense reasoning. Experiments on this dataset demonstrate that the performance of state-of-the-art MRC systems fall far behind human performance. ReCoRD represents a challenge for future research to bridge the gap between human and machine commonsense reading comprehension. ReCoRD is available at http://nlp.jhu.edu/record. Published 2018-10-30 6 authors [View paper](https://savrn.com/papers/record-bridging-the-gap-between-human-and-machine-commonsense-reading-comprehension) Paper ### [TallyQA: Answering Complex Counting Questions](https://savrn.com/papers/tallyqa-answering-complex-counting-questions) Most counting questions in visual question answering (VQA) datasets are simple and require no more than object detection. Here, we study algorithms for complex counting questions that involve relationships between objects, attribute identification, reasoning, and more. To do this, we created TallyQA, the world's largest dataset for open-ended counting. We propose a new algorithm for counting that uses relation… Published 2018-10-29 3 authors Code linked [View paper](https://savrn.com/papers/tallyqa-answering-complex-counting-questions) Paper ### [WikiHow: A Large Scale Text Summarization Dataset](https://savrn.com/papers/wikihow-a-large-scale-text-summarization-dataset) Sequence-to-sequence models have recently gained the state of the art performance in summarization. However, not too many large-scale high-quality datasets are available and almost all the available ones are mainly news articles with specific writing style. Moreover, abstractive human-style systems involving description of the content at a deeper level require data with higher levels of abstraction. In this paper… Published 2018-10-18 2 authors [View paper](https://savrn.com/papers/wikihow-a-large-scale-text-summarization-dataset) Paper ### [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://savrn.com/papers/bert-pre-training-of-deep-bidirectional-transformers-for-language-understanding) We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be fine-tuned with just one additional… Published 2018-10-11 4 authors [View paper](https://savrn.com/papers/bert-pre-training-of-deep-bidirectional-transformers-for-language-understanding) Paper ### [XNLI: Evaluating Cross-lingual Sentence Representations](https://savrn.com/papers/xnli-evaluating-cross-lingual-sentence-representations) State-of-the-art natural language processing systems rely on supervision in the form of annotated data to learn competent models. These models are generally trained on data in a single language (usually English), and cannot be directly used beyond that language. Since collecting data in every language is not realistic, there has been a growing interest in cross-lingual language understanding (XLU) and low-resource… Published 2018-09-13 7 authors Code linked [View paper](https://savrn.com/papers/xnli-evaluating-cross-lingual-sentence-representations) Paper ### [WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations](https://savrn.com/papers/wic-the-word-in-context-dataset-for-evaluating-context-sensitive-meaning-representations) By design, word embeddings are unable to model the dynamic nature of words' semantics, i.e., the property of words to correspond to potentially different meanings. To address this limitation, dozens of specialized meaning representation techniques such as sense or contextualized embeddings have been proposed. However, despite the popularity of research on this topic, very few evaluation benchmarks exist that… Published 2018-08-28 2 authors [View paper](https://savrn.com/papers/wic-the-word-in-context-dataset-for-evaluating-context-sensitive-meaning-representations) Paper ### [Unified Perceptual Parsing for Scene Understanding](https://savrn.com/papers/unified-perceptual-parsing-for-scene-understanding) Humans recognize the visual world at multiple levels: we effortlessly categorize scenes and detect objects inside, while also identifying the textures and surfaces of the objects along with their different compositional parts. In this paper, we study a new task called Unified Perceptual Parsing, which requires the machine vision systems to recognize as many visual concepts as possible from a given image. A… Published 2018-07-26 5 authors [View paper](https://savrn.com/papers/unified-perceptual-parsing-for-scene-understanding) Paper ### [Representation Learning with Contrastive Predictive Coding](https://savrn.com/papers/representation-learning-with-contrastive-predictive-coding) While supervised learning has enabled great progress in many applications, unsupervised learning has not seen such widespread adoption, and remains an important and challenging endeavor for artificial intelligence. In this work, we propose a universal unsupervised learning approach to extract useful representations from high-dimensional data, which we call Contrastive Predictive Coding. The key insight of our model… Published 2018-07-10 3 authors [View paper](https://savrn.com/papers/representation-learning-with-contrastive-predictive-coding) Paper ### [A Simple Method for Commonsense Reasoning](https://savrn.com/papers/a-simple-method-for-commonsense-reasoning) Commonsense reasoning is a long-standing challenge for deep learning. For example, it is difficult to use neural networks to tackle the Winograd Schema dataset (Levesque et al., 2011). In this paper, we present a simple method for commonsense reasoning with neural networks, using unsupervised learning. Key to our method is the use of language models, trained on a massive amount of unlabled data, to score multiple… Published 2018-06-07 2 authors [View paper](https://savrn.com/papers/a-simple-method-for-commonsense-reasoning) Paper ### [Neural Network Acceptability Judgments](https://savrn.com/papers/neural-network-acceptability-judgments) This paper investigates the ability of artificial neural networks to judge the grammatical acceptability of a sentence, with the goal of testing their linguistic competence. We introduce the Corpus of Linguistic Acceptability (CoLA), a set of 10,657 English sentences labeled as grammatical or ungrammatical from published linguistics literature. As baselines, we train several recurrent neural network models on… Published 2018-05-31 3 authors [View paper](https://savrn.com/papers/neural-network-acceptability-judgments) Paper ### [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://savrn.com/papers/glue-a-multi-task-benchmark-and-analysis-platform-for-natural-language-understanding) For natural language understanding (NLU) technology to be maximally useful, both practically and as a scientific object of study, it must be general: it must be able to process language in a way that is not exclusively tailored to any one specific task or dataset. In pursuit of this objective, we introduce the General Language Understanding Evaluation benchmark (GLUE), a tool for evaluating and analyzing the… Published 2018-04-20 6 authors [View paper](https://savrn.com/papers/glue-a-multi-task-benchmark-and-analysis-platform-for-natural-language-understanding) Paper ### [ESPnet: End-to-End Speech Processing Toolkit](https://savrn.com/papers/espnet-end-to-end-speech-processing-toolkit) This paper introduces a new open source platform for end-to-end speech processing named ESPnet. ESPnet mainly focuses on end-to-end automatic speech recognition (ASR), and adopts widely-used dynamic neural network toolkits, Chainer and PyTorch, as a main deep learning engine. ESPnet also follows the Kaldi ASR toolkit style for data processing, feature extraction/format, and recipes to provide a complete setup for… Published 2018-03-30 12 authors [View paper](https://savrn.com/papers/espnet-end-to-end-speech-processing-toolkit) Paper ### [Generalized End-to-End Loss for Speaker Verification](https://savrn.com/papers/generalized-end-to-end-loss-for-speaker-verification) In this paper, we propose a new loss function called generalized end-to-end (GE2E) loss, which makes the training of speaker verification models more efficient than our previous tuple-based end-to-end (TE2E) loss function. Unlike TE2E, the GE2E loss function updates the network in a way that emphasizes examples that are difficult to verify at each step of the training process. Additionally, the GE2E loss does not… Published 2017-10-28 4 authors [View paper](https://savrn.com/papers/generalized-end-to-end-loss-for-speaker-verification) Paper ### [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://savrn.com/papers/semeval-2017-task-1-semantic-textual-similarity-multilingual-and-cross-lingual-focused-eva) Semantic Textual Similarity (STS) measures the meaning similarity of sentences. Applications include machine translation (MT), summarization, generation, question answering (QA), short answer grading, semantic search, dialog and conversational systems. The STS shared task is a venue for assessing the current state-of-the-art. The 2017 task focuses on multilingual and cross-lingual pairs with one sub-track exploring… Published 2017-07-31 5 authors Code linked [View paper](https://savrn.com/papers/semeval-2017-task-1-semantic-textual-similarity-multilingual-and-cross-lingual-focused-eva) Paper ### [Attention Is All You Need](https://savrn.com/papers/attention-is-all-you-need) The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two… Published 2017-06-12 8 authors [View paper](https://savrn.com/papers/attention-is-all-you-need) Paper ### [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://savrn.com/papers/triviaqa-a-large-scale-distantly-supervised-challenge-dataset-for-reading-comprehension) We present TriviaQA, a challenging reading comprehension dataset containing over 650K question-answer-evidence triples. TriviaQA includes 95K question-answer pairs authored by trivia enthusiasts and independently gathered evidence documents, six per question on average, that provide high quality distant supervision for answering the questions. We show that, in comparison to other recently introduced large-scale… Published 2017-05-09 4 authors Code linked [View paper](https://savrn.com/papers/triviaqa-a-large-scale-distantly-supervised-challenge-dataset-for-reading-comprehension) Paper ### [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://savrn.com/papers/a-broad-coverage-challenge-corpus-for-sentence-understanding-through-inference) This paper introduces the Multi-Genre Natural Language Inference (MultiNLI) corpus, a dataset designed for use in the development and evaluation of machine learning models for sentence understanding. In addition to being one of the largest corpora available for the task of NLI, at 433k examples, this corpus improves upon available resources in its coverage: it offers data from ten distinct genres of written and… Published 2017-04-18 3 authors [View paper](https://savrn.com/papers/a-broad-coverage-challenge-corpus-for-sentence-understanding-through-inference) Paper ### [SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine](https://savrn.com/papers/searchqa-a-new-q-a-dataset-augmented-with-context-from-a-search-engine) We publicly release a new large-scale dataset, called SearchQA, for machine comprehension, or question-answering. Unlike recently released datasets, such as DeepMind CNN/DailyMail and SQuAD, the proposed SearchQA was constructed to reflect a full pipeline of general question-answering. That is, we start not from an existing article and generate a question-answer pair, but start from an existing question-answer pair… Published 2017-04-18 6 authors [View paper](https://savrn.com/papers/searchqa-a-new-q-a-dataset-augmented-with-context-from-a-search-engine) Paper ### [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://savrn.com/papers/squad-100-000-questions-for-machine-comprehension-of-text) We present the Stanford Question Answering Dataset (SQuAD), a new reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles, where the answer to each question is a segment of text from the corresponding reading passage. We analyze the dataset to understand the types of reasoning required to answer the questions, leaning heavily on dependency and constituency… Published 2016-06-16 4 authors [View paper](https://savrn.com/papers/squad-100-000-questions-for-machine-comprehension-of-text) Paper ### [Deep Residual Learning for Image Recognition](https://savrn.com/papers/deep-residual-learning-for-image-recognition) Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are… Published 2015-12-10 4 authors [View paper](https://savrn.com/papers/deep-residual-learning-for-image-recognition) Paper ### [Algorithms for the Markov Entropy Decomposition](https://savrn.com/papers/algorithms-for-the-markov-entropy-decomposition) The Markov entropy decomposition (MED) is a recently-proposed, cluster-based simulation method for finite temperature quantum systems with arbitrary geometry. In this paper, we detail numerical algorithms for performing the required steps of the MED, principally solving a minimization problem with a preconditioned Newton's algorithm, as well as how to extract global susceptibilities and thermal responses. We… Published 2012-12-06 2 authors [View paper](https://savrn.com/papers/algorithms-for-the-markov-entropy-decomposition) ## Model Collections Hand-picked starting points, each with the reason it exists. Collection · 4 entries ### [Embedding models for retrieval](https://savrn.com/collections/embedding-models-for-retrieval) Sentence and document embedding models used to build retrieval systems. Dimension and sequence length matter more than size here, and both come from the publisher. [View collection](https://savrn.com/collections/embedding-models-for-retrieval) Collection · 4 entries ### [Models that fit on one accelerator](https://savrn.com/collections/models-that-run-on-one-accelerator) Models whose publisher-reported parameter count puts them within reach of a single accelerator at common precisions. Memory needed depends on precision and serving configuration, so treat the parameter count as the starting point, not the answer. [View collection](https://savrn.com/collections/models-that-run-on-one-accelerator) Collection · 6 entries ### [Open-weight text models worth knowing](https://savrn.com/collections/open-weight-text-models-worth-knowing) Widely used open-weight language models, chosen because each one is a distinct family rather than a variant of the one above it. Selection, not a ranking. [View collection](https://savrn.com/collections/open-weight-text-models-worth-knowing) Collection · 3 entries ### [Speech and audio models](https://savrn.com/collections/speech-and-audio) Recognition and synthesis models, grouped so the two directions are easy to compare. [View collection](https://savrn.com/collections/speech-and-audio) ## Related SAVRN Research The hub sits beside SAVRN's market data and infrastructure research: what models cost to run, and what it takes to run them. SAVRN Index ### [What open models cost to run](https://savrn.com/ai-index/pricing/open-models) The same open-weight model priced by every host that serves it, per million tokens. Research Hub ### [Data center trackers and maps](https://savrn.com/data-center-research) Moratoriums, permits, power, water and capital behind the facilities that run these models. Method ### [How the Model Hub is built](https://savrn.com/model-hub/methodology) Sources, evidence labels, refresh behaviour, and the limits of every comparison here.