Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models Paper • 2512.00590 • Published 12 days ago • 38
Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation Paper • 2511.14993 • Published 23 days ago • 222
Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization Paper • 2510.25616 • Published Oct 29 • 96
GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver Paper • 2510.17699 • Published Oct 20 • 24
Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs Paper • 2510.11288 • Published Oct 13 • 48
When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA Paper • 2510.04849 • Published Oct 6 • 113
OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features Paper • 2509.22033 • Published Sep 26 • 18
OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features Paper • 2509.22033 • Published Sep 26 • 18
OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features Paper • 2509.22033 • Published Sep 26 • 18 • 2
The Rogue Scalpel: Activation Steering Compromises LLM Safety Paper • 2509.22067 • Published Sep 26 • 27
The Rogue Scalpel: Activation Steering Compromises LLM Safety Paper • 2509.22067 • Published Sep 26 • 27
The Rogue Scalpel: Activation Steering Compromises LLM Safety Paper • 2509.22067 • Published Sep 26 • 27 • 2
IoT-MCP: Bridging LLMs and IoT Systems Through Model Context Protocol Paper • 2510.01260 • Published Sep 25 • 2 • 2