Copertina

LLMs can construct powerful representations and streamline sample-efficient supervised learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Demirel, Ilker, Shi, Lawrence, Hussain, Zeshan, Sontag, David
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Uncovering Bias Mechanisms in Observational Studies
di: Demirel, Ilker, et al.
Pubblicazione: (2025)

Towards efficient representation identification in supervised learning
di: Ahuja, Kartik, et al.
Pubblicazione: (2022)

Benchmarking Observational Studies with Experimental Data under Right-Censoring
di: Demirel, Ilker, et al.
Pubblicazione: (2024)

Prediction-powered Generalization of Causal Inferences
di: Demirel, Ilker, et al.
Pubblicazione: (2024)

Chain-of-thought obfuscation learned from output supervision can generalise to unseen tasks
di: Hadida, Nathaniel Mitrani, et al.
Pubblicazione: (2026)

LLMs can Schedule
di: Abgaryan, Henrik, et al.
Pubblicazione: (2024)

Large language models can learn and generalize steganographic chain-of-thought under process supervision
di: Skaf, Joey, et al.
Pubblicazione: (2025)

A self-supervised framework for learning whole slide representations
di: Hou, Xinhai, et al.
Pubblicazione: (2024)

Leveraging large language models for efficient representation learning for entity resolution
di: Xu, Xiaowei, et al.
Pubblicazione: (2024)

From task structures to world models: What do LLMs know?
di: Yildirim, Ilker, et al.
Pubblicazione: (2023)

No Need for Explanations: LLMs can implicitly learn from mistakes in-context
di: Alazraki, Lisa, et al.
Pubblicazione: (2025)

Self-supervised inter-intra period-aware ECG representation learning for detecting atrial fibrillation
di: Zhu, Xiangqian, et al.
Pubblicazione: (2024)

An overview of neural architectures for self-supervised audio representation learning from masked spectrograms
di: Yadav, Sarthak, et al.
Pubblicazione: (2025)

Universal scaling laws in quantum-probabilistic machine learning by tensor network towards interpreting representation and generalization powers
di: Bai, Sheng-Chen, et al.
Pubblicazione: (2024)

Perturbation: A simple and efficient adversarial tracer for representation learning in language models
di: Rozner, Joshua, et al.
Pubblicazione: (2026)

Humans can learn to detect AI-generated texts, or at least learn when they can't
di: Milička, Jiří, et al.
Pubblicazione: (2025)

Keep what you need : extracting efficient subnetworks from large audio representation models
di: Genova, David, et al.
Pubblicazione: (2025)

Self-supervised vision-langage alignment of deep learning representations for bone X-rays analysis
di: Englebert, Alexandre, et al.
Pubblicazione: (2024)

Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame Projections
di: Demirel, Berken Utku, et al.
Pubblicazione: (2025)

Resource-efficient Layer-wise Federated Self-supervised Learning
di: Tun, Ye Lin, et al.
Pubblicazione: (2024)

LLMs can Realize Combinatorial Creativity: Generating Creative Ideas via LLMs for Scientific Research
di: Gu, Tianyang, et al.
Pubblicazione: (2024)

LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking
di: Helff, Lukas, et al.
Pubblicazione: (2026)

Large Language Models, scientific knowledge and factuality: A framework to streamline human expert evaluation
di: Wysocka, Magdalena, et al.
Pubblicazione: (2023)

Quota-based debiasing can decrease representation of already underrepresented groups
di: Smirnov, Ivan, et al.
Pubblicazione: (2020)

Harnessing the power of LLMs for normative reasoning in MASs
di: Savarimuthu, Bastin Tony Roy, et al.
Pubblicazione: (2024)

Semantic representations emerge in biologically inspired ensembles of cross-supervising neural networks
di: Urbach, Roy, et al.
Pubblicazione: (2025)

Self-supervised learning on gene expression data
di: Dradjat, Kevin, et al.
Pubblicazione: (2025)

LLMs can be easily Confused by Instructional Distractions
di: Hwang, Yerin, et al.
Pubblicazione: (2025)

How well can LLMs provide planning feedback in grounded environments?
di: Li, Yuxuan, et al.
Pubblicazione: (2025)

Large language models streamline automated systematic review: A preliminary study
di: Chen, Xi, et al.
Pubblicazione: (2025)

Curriculum reinforcement learning with measurable task representation learning
di: Wen, Yongyan, et al.
Pubblicazione: (2026)

The impact of hyper automation on streamlining enterprise digital workflows
di: Ishaan Rathore
Pubblicazione: (2022)

Boosting multi-demographic federated learning for chest radiograph analysis using general-purpose self-supervised representations
di: Lotfinia, Mahshad, et al.
Pubblicazione: (2025)

How well can LLMs Grade Essays in Arabic?
di: Ghazawi, Rayed, et al.
Pubblicazione: (2025)

SS-DPPN: A self-supervised dual-path foundation model for the generalizable cardiac audio representation
di: Muna, Ummy Maria, et al.
Pubblicazione: (2025)

Online inductive learning from answer sets for efficient reinforcement learning exploration
di: Veronese, Celeste, et al.
Pubblicazione: (2025)

Generating Energy-efficient code with LLMs
di: Cappendijk, Tom, et al.
Pubblicazione: (2024)

Improved cystic hygroma detection from prenatal imaging using ultrasound-specific self-supervised representation learning
di: Megahed, Youssef, et al.
Pubblicazione: (2025)

Abnormalities and Disease Detection in Gastro-Intestinal Tract Images
di: Khan, Zeshan, et al.
Pubblicazione: (2026)

The promise and limits of LLMs in constructing proofs and hints for logic problems in intelligent tutoring systems
di: Tithi, Sutapa Dey, et al.
Pubblicazione: (2025)