7 papers
Trust Region Policy Distillation
Zhengpeng Xie, Li Lyna Zhang, Zeke Xie +1
Big goals are hard to achieve all at once; breaking them into small steps is wiser. We present Trust Region Policy Distillation (TOP-D), which transforms the notoriously unstable,…
LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts
Siyuan Wang, Gaokai Zhang, Li Lyna Zhang +4
Reasoning over long contexts is essential for large language models. While reinforcement learning (RL) enhances short-context reasoning by inducing "Aha" moments in chain-of-though…
rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset
Yifei Liu, Li Lyna Zhang, Yi Zhu +5
Advancing code reasoning in large language models (LLMs) is fundamentally limited by the scarcity of high-difficulty datasets, especially those with verifiable input-output test ca…
Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimization
Yuanye Liu, Jiahang Xu, Li Lyna Zhang +6
Large Language Models (LLMs) have shown significant capability across various tasks, with their real-world effectiveness often driven by prompt design. While recent research has fo…
Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
Microsoft, :, Abdelrahman Abouelenin +73
We introduce Phi-4-Mini and Phi-4-Multimodal, compact yet highly capable language and multimodal models. Phi-4-Mini is a 3.8-billion-parameter language model trained on high-qualit…
LongRoPE2: Near-Lossless LLM Context Window Scaling
Ning Shang, Li Lyna Zhang, Siyuan Wang +5
LongRoPE2 is a novel approach that extends the effective context window of pre-trained large language models (LLMs) to the target length, while preserving the performance on the or…