Mingqian Feng PRO

fmmarkmq's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers 5 months ago

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

upvoted a paper 8 months ago

Directional Reasoning Injection for Fine-Tuning MLLMs

Paper • 2510.15050 • Published Oct 16, 2025 • 12

upvoted a paper 9 months ago

FlowRL: Matching Reward Distributions for LLM Reasoning

Paper • 2509.15207 • Published Sep 18, 2025 • 119