DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models Paper • 2510.15015 • Published 13 days ago • 10
Fine-Grained Detection of Context-Grounded Hallucinations Using LLMs Paper • 2509.22582 • Published Sep 26 • 10
CRISP: Persistent Concept Unlearning via Sparse Autoencoders Paper • 2508.13650 • Published Aug 19 • 15
TabSTAR: A Foundation Tabular Model With Semantically Target-Aware Representations Paper • 2505.18125 • Published May 23 • 112
TokenVerse: Versatile Multi-concept Personalization in Token Modulation Space Paper • 2501.12224 • Published Jan 21 • 47
Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models Paper • 2501.06751 • Published Jan 12 • 32
LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations Paper • 2410.02707 • Published Oct 3, 2024 • 48
Make It Count: Text-to-Image Generation with an Accurate Number of Objects Paper • 2406.10210 • Published Jun 14, 2024 • 78