DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models Paper • 2510.15015 • Published Oct 16, 2025 • 10
ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs Paper • 2510.00857 • Published Oct 1, 2025 • 1
Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models Paper • 2504.01137 • Published Apr 1, 2025 • 21
Trust Me, I'm Wrong: High-Certainty Hallucinations in LLMs Paper • 2502.12964 • Published Feb 18, 2025 • 3
Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models Paper • 2501.06751 • Published Jan 12, 2025 • 32