4 papers
Delta Rectified Flow Sampling for Text-to-Image Editing
Gaspard Beaudouin, Minghan Li, Jaeyeon Kim +2
We propose Delta Rectified Flow Sampling (DRFS), a novel inversion-free, path-aware editing framework within rectified flow models for text-to-image editing. DRFS is a distillation…
TrustTrade: Human-Inspired Selective Consensus Reduces Decision Uncertainty in LLM Trading Agents
Minghan Li, Rachel Gonsalves, Weiyue Li +2
Large language models (LLMs) are increasingly deployed as autonomous agents in financial trading. However, they often exhibit a hazardous behavioral bias that we term uniform trust…
TrailBlazer: History-Guided Reinforcement Learning for Black-Box LLM Jailbreaking
Sung-Hoon Yoon, Ruizhi Qian, Minda Zhao +2
Large Language Models (LLMs) have become integral to many domains, making their safety a critical priority. Prior jailbreaking research has explored diverse approaches, including p…
SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing
Sung-Hoon Yoon, Minghan Li, Gaspard Beaudouin +3
Rectified flow models have become a de facto standard in image generation due to their stable sampling trajectories and high-fidelity outputs. Despite their strong generative capab…