NeuroGenesysThe research we build on.
1,514 papers by other researchers that our work cites, from continual learning and verification to language models, agents and hardware. Each entry links to the paper on arXiv and to where we use it. 301 are cited on published pages of this site; the rest in the research notes behind our studies. Our own papers are in the archive.
- 2024-02arXiv 2402.19379Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracy
Philipp Schoenegger, Indre Tuminauskaite, Peter S. Park et al. · Society, software & economics
Human forecasting accuracy in practice relies on the 'wisdom of the crowd' effect, in which predictions about future events are significantly improved by aggregating across a crowd of individual forecasters.
- 2024-02arXiv 2402.05859Learning to Route Among Specialized Experts for Zero-Shot Generalization
Mohammed Muqeeth, Haokun Liu, Yufan Liu et al. · Machine learning
Recently, there has been a widespread proliferation of "expert" language models that are specialized to a specific task or domain through parameter-efficient fine-tuning.
- 2024-01arXiv 2401.16386Continual Learning with Pre-Trained Models: A Survey
Da-Wei Zhou, Hai-Long Sun, Jingyi Ning et al. · Machine learning
Nowadays, real-world applications often face streaming data, which requires the learning system to absorb new knowledge as data evolves. Continual Learning (CL) aims to achieve this goal and meanwhile overcome the catastrophic forgetting of former knowledge when learning new ones.
- 2023-12arXiv 2312.01188Efficient Expansion and Gradient Based Task Inference for Replay Free Incremental Learning
Soumya Roy, Vinay K Verma, Deepak Gupta · Machine learning
This paper proposes a simple but highly efficient expansion-based model for continual learning. The recent feature transformation, masking and factorization-based methods are efficient, but they grow the model only over the global or shared parameter.
- 2023-11arXiv 2311.09677R-Tuning: Instructing Large Language Models to Say `I Don't Know'
Hanning Zhang, Shizhe Diao, Yong Lin et al. · Language models & NLP
Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. A predominant issue is the propensity for these models to generate non-existent facts, a concern termed hallucination.
- 2023-10arXiv 2310.07234Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality
Liyuan Wang, Jingyi Xie, Xingxing Zhang et al. · Machine learning
Prompt-based continual learning is an emerging direction in leveraging pre-trained knowledge for downstream continual learning, and has almost reached the performance pinnacle under supervised pre-training.
- 2023-09arXiv 2309.15048Class Incremental Learning via Likelihood Ratio Based Task Prediction
Haowei Lin, Yijia Shao, Weinan Qian et al. · ICLR 2024 · Machine learning
Class incremental learning (CIL) is a challenging setting of continual learning, which learns a series of tasks sequentially. Each task consists of a set of unique classes.
- 2023-09arXiv 2309.14062FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
Dipam Goswami, Yuyang Liu, Bartłomiej Twardowski et al. · Vision
Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits the rehearsal of data from previous tasks and thus suffers from catastrophic forgetting.
- 2023-09arXiv 2309.13415Dream the Impossible: Outlier Imagination with Diffusion Models
Xuefeng Du, Yiyou Sun, Xiaojin Zhu et al. · Machine learning
Utilizing auxiliary outlier datasets to regularize the machine learning model has demonstrated promise for out-of-distribution (OOD) detection and safe prediction.
- 2023-07arXiv 2307.02251RanPAC: Random Projections and Pre-trained Models for Continual Learning
Mark D. McDonnell, Dong Gong, Amin Parveneh et al. · 37th Annual Conference on Neural Information Processing Systems (NeurIPS 2023), Dec 2023, New Orleans, United States · Machine learning
Continual learning (CL) aims to incrementally learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. Most CL works focus on tackling catastrophic forgetting under a learning-from-scratch paradigm.
- 2023-06arXiv 2306.12646Learnability and Algorithm for Continual Learning
Gyuhak Kim, Changnan Xiao, Tatsuya Konishi et al. · Machine learning
This paper studies the challenging continual learning (CL) setting of Class Incremental Learning (CIL). CIL learns a sequence of tasks consisting of disjoint sets of concepts or classes.
- 2023-06arXiv 2306.09301OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection
Jingyang Zhang, Jingkang Yang, Pengyun Wang et al. · Machine learning
Out-of-Distribution (OOD) detection is critical for the reliable operation of open-world intelligent systems. Despite the emergence of an increasing number of OOD detection methods, the evaluation inconsistencies present challenges for tracking the progress in this field.
- 2023-06arXiv 2306.03341Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
Kenneth Li, Oam Patel, Fernanda Viégas et al. · Machine learning
We introduce Inference-Time Intervention (ITI), a technique designed to enhance the "truthfulness" of large language models (LLMs). ITI operates by shifting model activations during inference, following a set of directions across a limited number of attention heads.
- 2023-03arXiv 2303.08774GPT-4 Technical Report
OpenAI, Josh Achiam, Steven Adler et al. · Language models & NLP
We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs.
- 2023-03arXiv 2303.02966Non-Parametric Outlier Synthesis
Leitian Tao, Xuefeng Du, Xiaojin Zhu et al. · Machine learning
Out-of-distribution (OOD) detection is indispensable for safely deploying machine learning models in the wild. One of the key challenges is that models lack supervision signals from unknown data, and as a result, can produce overconfident predictions on OOD data.
- 2022-11arXiv 2211.02633A Theoretical Study on Solving Continual Learning
Gyuhak Kim, Changnan Xiao, Tatsuya Konishi et al. · Machine learning
Continual learning (CL) learns a sequence of tasks incrementally. There are two popular CL settings, class incremental learning (CIL) and task incremental learning (TIL).
Cited inThe Capacity AuditInvestors are paying for agents that learn on the job. The hard part is knowing what they forgot.Penalising wrong answers only works if someone else is gradingStudy: Forgetting as selection at scaleStudy: Genesys program prior artInternal notesStudy: Orchestrated specialists and bridge synthesisStudy: Stopping confident wrong expert votes - 2022-10arXiv 2210.16955Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles
Rajeev Verma, Daniel Barrejón, Eric Nalisnick · Machine learning
We study the statistical properties of learning to defer (L2D) to multiple experts. In particular, we address the open problems of deriving a consistent surrogate loss, confidence calibration, and principled ensembling of experts.
- 2022-10arXiv 2210.10760Scaling Laws for Reward Model Overoptimization
Leo Gao, John Schulman, Jacob Hilton · Machine learning
In reinforcement learning from human feedback, it is common to optimize against a reward model trained to predict human preferences. Because the reward model is an imperfect proxy, optimizing its value too much can hinder ground truth performance, in accordance with Goodhart's law.
Cited inReal judges did not break Best-of-N at N ≤ 32, and measured ε did not predict the budgetThurstone Bounds Best-of-N: A 1927 Identity, Calibrated for Modern VerifiersStudy: Generational competitive continual learningStudy: Genesys program prior artInternal notesStudy: Judge exploitability on real Best-of-NStudy: Logical coherence of LLM world modelsStudy: Stopping confident wrong expert votes - 2022-08arXiv 2208.09734A Multi-Head Model for Continual Learning via Out-of-Distribution Replay
Gyuhak Kim, Zixuan Ke, Bing Liu · Machine learning
This paper studies class incremental learning (CIL) of continual learning (CL). Many approaches have been proposed to deal with catastrophic forgetting (CF) in CIL.
- 2022-07arXiv 2207.05221Language Models (Mostly) Know What They Know
Saurav Kadavath, Tom Conerly, Amanda Askell et al. · Language models & NLP
We study whether language models can evaluate the validity of their own claims and predict which questions they will be able to answer correctly. We first show that larger models are well-calibrated on diverse multiple choice and true/false questions when they are provided in the right format.
- 2022-04arXiv 2204.06507Out-of-Distribution Detection with Deep Nearest Neighbors
Yiyou Sun, Yifei Ming, Xiaojin Zhu et al. · Machine learning
Out-of-distribution (OOD) detection is a critical task for deploying machine learning models in the open world. Distance-based methods have demonstrated promise, where testing samples are detected as OOD if they are relatively far away from in-distribution (ID) data.
- 2022-02arXiv 2202.01197VOS: Learning What You Don't Know by Virtual Outlier Synthesis
Xuefeng Du, Zhaoning Wang, Mu Cai et al. · Machine learning
Out-of-distribution (OOD) detection has received much attention lately due to its importance in the safe deployment of neural networks. One of the key challenges is that models lack supervision signals from unknown data, and as a result, can produce overconfident predictions on OOD data.
- 2021-06arXiv 2106.09022A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection
Jie Ren, Stanislav Fort, Jeremiah Liu et al. · Machine learning
Mahalanobis distance (MD) is a simple and popular post-processing method for detecting out-of-distribution (OOD) inputs in neural networks.
- 2021-04arXiv 2104.03344OVANet: One-vs-All Network for Universal Domain Adaptation
Kuniaki Saito, Kate Saenko · Vision
Universal Domain Adaptation (UNDA) aims to handle both domain-shift and category-shift between two datasets, where the main challenge is to transfer knowledge while rejecting unknown classes which are absent in the labeled source data but present in the unlabeled target data.
- 2021-03arXiv 2103.00953Adversarial Reciprocal Points Learning for Open Set Recognition
Guangyao Chen, Peixi Peng, Xiangqian Wang et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence 2021 · Vision
The key challenge of OSR is how to reduce the empirical classification risk on the labeled known data and the open space risk on the potential unknown data simultaneously.
- 2021-02arXiv 2102.11582Deep Deterministic Uncertainty: A Simple Baseline
Jishnu Mukhoti, Andreas Kirsch, Joost van Amersfoort et al. · Machine learning
Reliable uncertainty from deterministic single-forward pass models is sought after because conventional methods of uncertainty quantification are computationally expensive.
- 2020-10arXiv 2010.03759Energy-based Out-of-distribution Detection
Weitang Liu, Xiaoyun Wang, John D. Owens et al. · Machine learning
Determining whether inputs are out-of-distribution (OOD) is an essential building block for safely deploying machine learning models in the open world. However, previous methods relying on the softmax confidence score suffer from overconfident posterior distributions for OOD data.
- 2020-07arXiv 2007.08176CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
Jihoon Tack, Sangwoo Mo, Jongheon Jeong et al. · Machine learning
, identifying whether a given sample is drawn from outside the training distribution, is essential for reliable machine learning. To this end, there have been many attempts at learning a representation well-suited for novelty detection and designing a score based on such representation.
- 2020-07arXiv 2007.05134Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networks
Shreyas Padhy, Zachary Nado, Jie Ren et al. · Machine learning
Accurate estimation of predictive uncertainty in modern neural networks is critical to achieve well calibrated predictions and detect out-of-distribution (OOD) inputs.
- 2020-06arXiv 2006.10108Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness
Jeremiah Zhe Liu, Zi Lin, Shreyas Padhy et al. · Machine learning
Bayesian neural networks (BNN) and deep ensembles are principled approaches to estimate the predictive uncertainty of a deep learning model. However their practicality in real-time, industrial-scale applications are limited due to their heavy memory and inference cost.
- 2020-04arXiv 2004.03473Learning from Imperfect Annotations
Emmanouil Antonios Platanios, Maruan Al-Shedivat, Eric Xing et al. · Machine learning
Many machine learning systems today are trained on large amounts of human-annotated data. Data annotation tasks that require a high level of competency make data acquisition expensive, while the resulting labels are often subjective, inconsistent, and may contain a variety of human biases.
- 2019-06arXiv 1907.00208Deep Gamblers: Learning to Abstain with Portfolio Theory
Liu Ziyin, Zhikang Wang, Paul Pu Liang et al. · Machine learning
We deal with the \textit{selective classification} problem (supervised-learning problem with a rejection option), where we want to achieve the best performance at a certain level of coverage of the data.
- 2019-01arXiv 1901.09192SelectiveNet: A Deep Neural Network with an Integrated Reject Option
Yonatan Geifman, Ran El-Yaniv · Machine learning
We consider the problem of selective prediction (also known as reject option) in deep neural networks, and introduce SelectiveNet, a deep neural architecture with an integrated reject option.
- 2018-12arXiv 1812.05720Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem
Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf · Machine learning
Classifiers used in the wild, in particular for safety-critical systems, should not only have good generalization properties but also should know when they don't know, in particular make low confidence predictions far away from the training data.
- 2018-12arXiv 1812.04606Deep Anomaly Detection with Outlier Exposure
Dan Hendrycks, Mantas Mazeika, Thomas Dietterich · Machine learning
It is important to detect anomalous inputs when deploying machine learning systems. The use of larger and more complex inputs in deep learning magnifies the difficulty of distinguishing between anomalous and in-distribution examples.
- 2018-11arXiv 1811.00217META-DES.Oracle: Meta-learning and feature selection for ensemble selection
Rafael M. O Cruz, Robert Sabourin, George D. C. Cavalcanti · Volume 38, November 2017, Pages 84-103 · Machine learning
The key issue in Dynamic Ensemble Selection (DES) is defining a suitable criterion for calculating the classifiers' competence. There are several criteria available to measure the level of competence of base classifiers, such as local accuracy estimates and ranking.
- 2018-11arXiv 1811.01743On Meta-Learning for Dynamic Ensemble Selection
Rafael M. O. Cruz, Robert Sabourin, George D. C. Cavalcanti · Published on the International Conference on Pattern Recognition (ICPR), 2014, pp. 1230-1235 · Machine learning
In this paper, we propose a novel dynamic ensemble selection framework using meta-learning. The framework is divided into three steps. In the first step, the pool of classifiers is generated from the training data.
- 2018-09arXiv 1810.01270META-DES: A Dynamic Ensemble Selection Framework using Meta-Learning
Rafael M. O. Cruz, Robert Sabourin, George D. C. Cavalcanti et al. · Pattern Recognition Volume 48, Issue 5, Pages 1925-1935 · Machine learning
Dynamic ensemble selection systems work by estimating the level of competence of each classifier from a pool of classifiers. Only the most competent ones are selected to classify a given test sample.
- 2017-11arXiv 1711.10160Snorkel: Rapid Training Data Creation with Weak Supervision
Alexander Ratner, Stephen H. Bach, Henry Ehrenberg et al. · Proceedings of the VLDB Endowment, 11(3), 269-282, 2017 · Machine learning
Labeling training data is increasingly the largest bottleneck in deploying machine learning systems. We present Snorkel, a first-of-its-kind system that enables users to train state-of-the-art models without hand labeling any training data.
- 2017-05arXiv 1705.08500Selective Classification for Deep Neural Networks
Yonatan Geifman, Ran El-Yaniv · Machine learning
Selective classification techniques (also known as reject option) have not yet been considered in the context of deep neural networks (DNNs). These techniques can potentially significantly improve DNNs prediction performance by trading-off coverage.
Built from every arXiv paper cited in our papers, posts, topic hubs, reports and research notes, with titles, authors, dates and abstracts from the arXiv API (updated 2026-11-12). Summaries are the opening sentences of each paper's own abstract, not our assessment; a citation means we used or checked the work, not that we endorse it. Fields follow each paper's primary arXiv category. Papers cited only outside arXiv (journals, proceedings) are not listed yet. Entries are generated from our citations, so a mistyped ID in a note would list the wrong paper; we remove those as we find them. Report a wrong entry.
