Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models Paper • 2512.00590 • Published Nov 29, 2025 • 48
Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation Paper • 2511.14993 • Published Nov 19, 2025 • 230
Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization Paper • 2510.25616 • Published Oct 29, 2025 • 98
GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver Paper • 2510.17699 • Published Oct 20, 2025 • 25
Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs Paper • 2510.11288 • Published Oct 13, 2025 • 49
When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA Paper • 2510.04849 • Published Oct 6, 2025 • 115
OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features Paper • 2509.22033 • Published Sep 26, 2025 • 19
OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features Paper • 2509.22033 • Published Sep 26, 2025 • 19
OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features Paper • 2509.22033 • Published Sep 26, 2025 • 19 • 2
The Rogue Scalpel: Activation Steering Compromises LLM Safety Paper • 2509.22067 • Published Sep 26, 2025 • 28
The Rogue Scalpel: Activation Steering Compromises LLM Safety Paper • 2509.22067 • Published Sep 26, 2025 • 28
The Rogue Scalpel: Activation Steering Compromises LLM Safety Paper • 2509.22067 • Published Sep 26, 2025 • 28 • 2
IoT-MCP: Bridging LLMs and IoT Systems Through Model Context Protocol Paper • 2510.01260 • Published Sep 25, 2025 • 3 • 2