vector-institute/Qwen3-8B-UnBias-Plus-SFT-Instruct-Legacy
Text Generation • 8B • Updated • 636 •
None defined yet.
When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gains
LoopFormer: Elastic-Depth Looped Transformers for Latent Reasoning via Shortcut Modulation