Thanawat Lodkaew

skydddoogg's activity

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

upvoted a paper 2 days ago

Mitigating Reward Hacking in RLHF via Advantage Sign Robustness

Paper • 2604.02986 • Published Apr 3 • 3

upvoted 2 papers 15 days ago

How Can I Publish My LLM Benchmark Without Giving the True Answers Away?

Paper • 2505.18102 • Published May 23, 2025 • 2

Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests

Paper • 2606.07379 • Published 21 days ago • 5