Home | Tags | #p-kasneci-gjergji

#p-kasneci-gjergji

LK26b

Safety Cost of Steering Vectors Is Separable and Reducible

AI4GOOD @ICML 2026

#p-kasneci-gjergji
Read more

LK26a

Safety Cost of Steering Vectors Is Separable and Reducible

CompLearn @ICML 2026

#p-kasneci-gjergji
Read more

ARS+26

When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation

ICML 2026

#p-kasneci-gjergji
Read more

KK26a

Sycophancy Is an Educational Safety Risk: Why LLM Tutors Need Sycophancy Benchmarks

ICML 2026

#p-kasneci-enkelejda #p-kasneci-gjergji
Read more

ZYP+26

Active Tabular Augmentation via Policy-Guided Diffusion Inpainting

ICML 2026

#p-kasneci-gjergji
Read more

WNB+26

One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization

ACL 2026

#p-kasneci-gjergji
Read more

YZP+26

SAGE: Sparse Adaptive Guidance for Dependency-Aware Tabular Data Generation

ACL 2026

#p-kasneci-gjergji
Read more

YZK26

Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models

ACL 2026

#p-kasneci-gjergji
Read more

LFZ+26

Analysing the Safety Pitfalls of Steering Vectors

Findings @ACL 2026

#p-kasneci-gjergji
Read more

BNS+26

Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results

Preprint (Jun. 2026)

#p-kasneci-gjergji
Read more

ZPK+26

Reinforcement Unlearning via Group Relative Policy Optimization

ICLR 2026

#p-kasneci-gjergji
Read more

JPS+26

TabSCM: A Practical Framework for Generating Realistic Tabular Data

Preprint (Apr. 2026)

#p-kasneci-gjergji
Read more

SOK+26

Efficient General Intelligence Through Multi-Component Integration

Preprint (Apr. 2026)

#p-kasneci-gjergji
Read more

FSK+26

RIBEX: Predicting and Explaining RNA Binding Across Structured and Intrinsically Disordered Regions (IDR)-Rich Proteins

Preprint (Mar. 2026)

#p-kasneci-gjergji
Read more

YMZ+26

Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs

Preprint (Jan. 2026)

#p-kasneci-gjergji #p-kreuter
Read more

WMZ+25

Evaluating Zero-Shot Multilingual Aspect-Based Sentiment Analysis With Large Language Models

International Journal of Machine Learning and Cybernetics 16.10. Jun. 2025

#p-kasneci-gjergji #p-kreuter
Read more

ZYM+23a

Baby’s CoThought: Leveraging Large Language Models for Enhanced Reasoning in Compact Models

BabyLM Challenge @CoNLL 2023)

#p-kasneci-gjergji #p-kreuter #p-ruegamer #p-schuetze
Read more

MFJ+23

IPDP: On Partial Dependence Plots in Dynamic Modeling Scenarios

XAI 2023

#p-huellermeier #p-kasneci-gjergji
Read more
Back to Top

2018-12-10 - Last modified: 2018-12-10