ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

20 results for “self-supervised learning”

CS papers only

Hybrid search: Keyword + semantic, ranked by combined score.ⓘ

Want pure semantic search? Try claim verification →

cs.CVEmpiricalRecentJun 12, 2026

S$^2$COPE: Self-Supervised Concept Discovery via Preference Learning

Shilong Xiang, Zirui Zhang, Chengzhi Mao

This paper introduces a self-supervised framework for discovering novel, structured concepts from raw imagery without human annotation.

View →
cs.CRcs.LGApr 24, 2026

Self-Supervised Learning for Android Malware Detection on a Time-Stamped Dataset

Annan Fu, Hao Pei, Maryam Tanha

The paper proposes a time-aware self-supervised learning framework using BYOL to improve Android malware detection robustness by accurately accounting for app release times.

View →
cs.AIcs.CLcs.LGEmpiricalRecentSep 25, 2026

Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency

Parsa Hosseini, Akasha Tigalappanavara, Sumit Nawathe, Chenrui Fan +5 more

The authors improve the efficiency of reasoning models by fine-tuning them to predict their confidence in their answers, resulting in reduced generated tokens without sacrificing accuracy.

View →
eess.ASEmpiricalRecentJul 18, 2026

NABEATs: Noise-Aware Audio Representation Learning

Takuya Fujimura, Yoshiki Masuyama, Gordon Wichern, Christoph Boeddeker +2 more

The paper introduces Noise-Aware BEATs (NABEATs), a noise-aware audio self-supervised learning framework that estimates clean BEATs representations from noisy audio signals using an auxiliary referenc…

View →
cs.CLEmpiricalRecentJun 16, 2026

Learning from the Self-future: On-policy Self-distillation for dLLMs

Yifu Luo, Zeyu Chen, Haoyu Wang, Xinhao Hu +3 more

This paper introduces a new on-policy self-distillation framework tailored for diffusion large language models.

View →
cs.IRcs.AIEmpiricalRecentJul 1, 2026

Real-Time Hard Negative Sampling via LLM-based Clustering for Large-Scale Two-Tower Retrieval

Ivan Ji, Liuyi Hu, Harrison, Zhao +5 more

A novel self-supervised hard negative sampling technique is proposed for two-tower recommendation systems using a large language model to generate challenging and informative negatives.

View →
cs.LGcs.AIcs.CVRecentJun 4, 2026

In-Context Multiple Instance Learning

Alexander Möllers, Marvin Sextro, Julius Hense, Gabriel Dernbach +1 more

The paper proposes pretraining a Perceiver-style in-context learner on synthetic data to solve Multiple Instance Learning (MIL) tasks efficiently in the low-label regime.

View →
cs.LGcs.AIcs.NEEmpiricalRecentOct 29, 2026

AutoHebb: Self-Modifying Neural Networks that Zero-Shot Infer and Continually Learn

Daniel Levine, David van Dijk, Kenneth Kay

The paper introduces AutoHebb, a class of online learning feedforward neural networks that realize strong inductive biases and autonomously controlled learning.

View →
cs.CLRecentMay 31, 2026

On the Generalization Gap in Self-Evolving Language Model Reasoning

Zhenting Qi, Susanna Maria Baby, Stefanie Anna Baby, Kan Yuan +4 more

The paper investigates the limits of self-evolution in LLM reasoning under closed-loop settings, finding that while self-improvement is significant, it consistently falls short of perfect oracle super…

View →
cs.CLRecentMay 29, 2026

The Flip Side of RLHF: On-Policy Feedback for Reward Model Self-Supervised Improvement

Xiaobo Wang, Tong Wu, Min Tang, Jiaqi Li +2 more

The paper introduces SAVE, a framework that uses on-policy feedback and the value function to self-supervise and improve reward models, significantly enhancing RLHF performance across multiple benchma…

View →
stat.MLcs.CCcs.DSTheoreticalRecentJul 7, 2026

Boosting with List-Decodable Codes

Addison Prairie, Li-Yang Tan

A new boosting algorithm that strong learns concept classes closed under O(log 1/γ)-XOR using O(log 1/ε) calls to a γ-advantage weak learner and additional samples, by connecting boosting with list-de…

View →
cs.AIRecentMay 29, 2026

Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight

Can Jin, Jiakang Li, Rui Wu, Eddy Zhang +1 more

The paper introduces Weak-Critic Strong Oversight, a method where a weak model guides a strong model's self-improvement by providing non-misleading revision directions, leading to scalable oversight.

View →
stat.MLcs.LGRecentJun 1, 2026

Doing well with less! On Sampling Techniques for Empirical Pairwise Loss Estimation/Minimization

Louise Davy, Stephan Clémençon, Charlotte Laclau

This paper introduces survey sampling techniques to estimate or minimize empirical pairwise loss functions, showing that targeting informative pairs significantly reduces computational cost while main…

View →
stat.MLcs.LGEmpiricalRecentJun 28, 2026

Gradient boosting with vector-valued leafs

David Cortes

This paper extends gradient boosting to functions of vector inputs using a simple algorithm with histogram-based decision trees.

View →
cs.CLEmpiricalRecentSep 25, 2026

Strategically Diverse Sampling for Self-Training

Alexander Gurung, Esmeralda S. Whitammer, Mirella Lapata

This paper investigates the use of strategically diverse data in self-training for LLMs, showing that diversity of approaches can matter more than correctness or teacher scale.

View →
cs.CLcs.AIcs.LGRecentMay 29, 2026

Not All Synthetic Data Is Yours to Learn From

Sina Alemohammad, Li Chen, Richard G. Baraniuk, Zhangyang Wang

Weak self-training on synthetic data can amplify a language model's existing capabilities, but this effect is strictly dependent on the compatibility between the source and student models, not on the…

View →
cs.MAcs.AIEmpiricalRecentJun 19, 2026

Cohort Organized Learning: Clustering Through Agreement

Finn Henry O'Shea, Maria Elena Monzani

This paper presents Cohort Organized Learning (CoOL), a method for clustering data without explicit distance or similarity computations.

View →
cs.LGcs.AIRecentMay 28, 2026

A Predictive Law for On-Policy Self-Distillation From World Feedback

Tommy He, Jerome Sieber, Matteo Saponati

The paper identifies a linear predictive law linking the initial performance gap in on-policy self-distillation (OPSD) to the final performance improvement, allowing researchers to anticipate and tune…

View →