SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks Paper • 2602.06854 • Published Feb 6 • 6
Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling Paper • 2601.22636 • Published Jan 30 • 22
Directional Reasoning Injection for Fine-Tuning MLLMs Paper • 2510.15050 • Published Oct 16, 2025 • 12
FlowRL: Matching Reward Distributions for LLM Reasoning Paper • 2509.15207 • Published Sep 18, 2025 • 118
