Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone Paper • 2512.22615 • Published 29 days ago • 48
SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving Paper • 2601.01426 • Published 21 days ago • 22
Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL Paper • 2505.17952 • Published May 23, 2025 • 20
Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models Paper • 2504.04823 • Published Apr 7, 2025 • 31