A. and Q

By Neil Genzlinger. 2006

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

Citations in the corpus

Direct Preference Optimization: Your Language Model is Secretly a Reward Model (2023, background): “However, their performance on downstream tasks and alignment with user intent can be significantly improved by fine-tuning on datasets of instructions and humanwritten completions [21, 33, 13, 36].”
TruthfulQA: Measuring How Models Mimic Human Falsehoods (2021, background): “TruthfulQA is intended as a zero-shot benchmark (Brown et al., 2020; Wei et al., 2021).”
The Capacity for Moral Self-Correction in Large Language Models (2023, background): “This phenomenon is sometimes referred to as “u-shaped” scaling [59].”
Attention Augmented Convolutional Networks (2019, methodology): “These datasets have been used as benchmarks for delineating better image featurizations and network architectures across a broad range of tasks [21].”
Byzantine-Resilient Secure Federated Learning (2020, background): “Distributed training protocols have been extensively studied in the Byzantine setting using clear (unmasked) model updates [9]–[13], [19], [20].”
Class-Incremental Continual Learning Into the eXtended DER-Verse (2022, methodology): “As stated by the authors of [69], a precise and wellestablished definition of visual concepts as well as the ways these can be quantified remain elusive matters.”
Cyberbullying Detection With Fairness Constraints (2020, background): “For instance, a recent study by Nadeem et al. show that stereotypical bias is ampliﬁed as pretrained language models (e.g. BERT [28], RoBERTa [43], XLNet [44], GPT-2 [30]) become stronger [42].”
Adversarial Symmetric Variational Autoencoder (2017, background): “Variational autoencoders (VAEs) are designed to learn both an encoder and decoder, leading to excellent data reconstruction and the ability to quantify a bound on the log-likelihood fit of the model to data [12, 13, 14, 15, 16, 17, 18, 19].”
Person Recognition in Personal Photo Collections (2015, background): “Both settings have seen a recent shift from sophisticated classifiers based on hand-crafted features and metric learning approaches [20, 7, 5, 29, 26, 41, 1], towards methods based on deep learning [37, 36, 43, 33, 27, 38, 21].”
Wireless Edge Computing With Latency and Reliability Guarantees (2019, background): “Low-Latency Enabler 3 (Edge Machine Learning): Inference (or prediction) capabilities with low latency are one of the main reasons for ML to be popular in MEC as well as several other communication applications such as coding, BF, resource optimization, caching, scheduling, routing, and security [18”
Grain Refinement of Magnesium Alloys: A Review of Recent Research, Theoretical Developments, and Their Application (2013, background): “Samarium (Sm) additions to Mg-Al alloys have also been found to be effective grain refiners.([112])”
Facile synthesis and superior electrochemical performances of CoNi2S4/graphene nanocomposite suitable for supercapacitor electrodes (2014, background): “In the XRD pattern of the GO, the typical sharp peak around 10 can 45 be detected, which corresponding to the (002) plane of GO.(5) After reduction, the GO peak disappeared and a broadened peak at 24.”
Modeling Cyber–Physical Systems (2012, methodology): “Our work has been demonstrated in the open-source software frameworks Ptolemy Classic [9], Ptolemy II [19], Polis [2], Metropolis [3], and MetroII [15].”