Minwu Kim's picture

3 7

Minwu Kim

guactastesgood

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 minutes ago

On the Limits of Layer Pruning for Generative Reasoning in LLMs

authored a paper about 17 hours ago

Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning

published a model about 21 hours ago

guactastesgood/DeepSeek-R1-Distill-Qwen-1.5B-failure-prefix-conditioning-iteration1

View all activity

Organizations

authored a paper about 17 hours ago

Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning

Paper • 2601.20829 • Published 6 days ago • 5

submitted a paper to Daily Papers 5 days ago

Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning

Paper • 2601.20829 • Published 6 days ago • 5

authored 2 papers 9 months ago

Reinforcement Learning vs. Distillation: Understanding Accuracy and Capability in LLM Reasoning

Paper • 2505.14216 • Published May 20, 2025 • 2

Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings

Paper • 2505.13718 • Published May 19, 2025 • 7

authored a paper 12 months ago

Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges

Paper • 2502.08680 • Published Feb 12, 2025 • 11