Great Models Think Alike and this Undermines AI Oversight
Paper
•
2502.04313
•
Published
•
31
post-training
post-train
·
AI & ML interests
None yet
Recent Activity
new activity
6 days ago
SynthLabsAI/Big-Math-RL-Verified:405b solve rate
liked
a Space
6 days ago
ameerazam08/PhotoDoodle-Image-Edit-GPU
liked
a dataset
6 days ago
SakanaAI/gsm8k-ja-test_250-1319
Organizations
post-train's activity
upvoted
7
papers
25 days ago
Fast Video Generation with Sliding Tile Attention
Paper
•
2502.04507
•
Published
•
49
AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360° Unbounded Scene Inpainting
Paper
•
2502.05176
•
Published
•
32
Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
Paper
•
2502.06781
•
Published
•
60
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
Paper
•
2502.06703
•
Published
•
142
Competitive Programming with Large Reasoning Models
Paper
•
2502.06807
•
Published
•
67
TextAtlas5M: A Large-scale Dataset for Dense Text Image Generation
Paper
•
2502.07870
•
Published
•
43