3 papers
cs.LG2025
ThetaEvolve: Test-time Learning on Open Problems
Yiping Wang, Shao-Rong Su, Zhiyuan Zeng +13
Recent advances in large language models (LLMs) have enabled breakthroughs in mathematical discovery, exemplified by AlphaEvolve, a closed-source system that evolves programs to im…
cs.CL2025
RL from Teacher-Model Refinement: Gradual Imitation Learning for Machine Translation
Dongyub Jude Lee, Zhenyi Ye, Pengcheng He
Preference-learning methods for machine translation (MT), such as Direct Preference Optimization (DPO), have shown strong gains but typically rely on large, carefully curated prefe…
cs.CL2025
Chain of Draft: Thinking Faster by Writing Less
Silei Xu, Wenhao Xie, Lingxiao Zhao +1
Large Language Models (LLMs) have demonstrated remarkable performance in solving complex reasoning tasks through mechanisms like Chain-of-Thought (CoT) prompting, which emphasizes…