Long-CoT SFT and RL trade off strengths in reasoning VLMs, and five combination strategies fail to produce additive gains.
Arcee’s mergekit: A toolkit for merging large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs
Long-CoT SFT and RL trade off strengths in reasoning VLMs, and five combination strategies fail to produce additive gains.