Abhinav Moudgil
@amoudgl.bsky.social
๐ค 179
๐ฅ 84
๐ 3
PhD student, Mila abhinavmoudgil.com
New side project! assayer: A simple Python-RQ based tool to automatically monitor and evaluate ML model checkpoints offline during training.
8 months ago
1
4
1
reposted by
Abhinav Moudgil
Aditi Mavalankar
11 months ago
Excited to share our recent work, AuPair, an inference-time technique that builds on the premise of in-context learning to improve LLM coding performance!
arxiv.org/abs/2502.18487
๐งต
loading . . .
AuPair: Golden Example Pairs for Code Repair
Scaling up inference-time compute has proven to be a valuable strategy in improving the performance of Large Language Models (LLMs) without fine-tuning. An important task that can benefit from additio...
https://arxiv.org/abs/2502.18487
1
12
7
you reached the end!!
feeds!
log in