Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum
Chu-Cheng Lin, Eugene Ie
SFT-then-RLVR is widely used for post-training reasoning models, but why this specific ordering, and why RLVR-only stalls at cold start, have lacked a unifying theoretical account.…
cs.LG2025
Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning
Shenao Zhang, Yaqing Wang, Yinxiao Liu +5
Large Language Models (LLMs) trained via Reinforcement Learning (RL) have exhibited strong reasoning capabilities and emergent reflective behaviors, such as rethinking and error co…
cs.LG2025
Improving Rectified Flow with Boundary Conditions
Xixi Hu, Runlong Liao, Keyang Xu +5
Rectified Flow offers a simple and effective approach to high-quality generative modeling by learning a velocity field. However, we identify a limitation in directly modeling the v…