Offline-RL

classroom

AI & ML interests

None defined yet.

submitted a paper to Daily Papers 2 months ago

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

Paper • 2602.01058 • Published Feb 1 • 43

authored a paper over 1 year ago

$\textbf{Only-IF}$:Revealing the Decisive Effect of Instruction Diversity on Generalization

Paper • 2410.04717 • Published Oct 7, 2024 • 18

authored 3 papers almost 2 years ago

Instruction Diversity Drives Generalization To Unseen Tasks

Paper • 2402.10891 • Published Feb 16, 2024

PACE-LM: Prompting and Augmentation for Calibrated Confidence Estimation with GPT-4 in Cloud Incident Root Cause Analysis

Paper • 2309.05833 • Published Sep 11, 2023

PLUM: Preference Learning Plus Test Cases Yields Better Code Language Models

Paper • 2406.06887 • Published Jun 11, 2024 • 2

authored a paper about 2 years ago

Transformer-Based Models Are Not Yet Perfect At Learning to Emulate Structural Recursion

Paper • 2401.12947 • Published Jan 23, 2024 • 4