7 papers
A Language Model from 1913: Pretraining on Historical Text
Xiaoxi Luo, Zachary Shinnick, Niclas Griesshaber +5
While modern language models increasingly rely on ever-larger web corpora, we show that pretraining on historical text (e.g., pre-1913 text) in a data-constrained setting can produ…
CARE-RL: Capability-Aware Reinforcement Learning for Mitigating Cross-Domain Conflicts
Rui Zhang, Xinle Wu, Yao Lu
Reinforcement learning (RL) with verifiable rewards has achieved strong progress in reasoning-oriented LLMs, but extending it to multi-domain RL remains challenging due to reward u…
Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards
Mengjie Ren, Jie Lou, Boxi Cao +6
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective paradigm for improving the reasoning capabilities of large language models. However, RLVR training…
PowerStep: Memory-Efficient Adaptive Optimization via -Norm Steepest Descent
Yao Lu, Dengdong Fan, Shixun Zhang +1
Adaptive optimizers such as Adam are standard for training Transformers, but storing gradient first and second moments incurs substantial memory overhead. We introduce PowerStep, a…
Automatic Configuration of LLM Post-Training Pipelines
Channe Chwa, Xinle Wu, Yao Lu
LLM post-training pipelines that combine supervised fine-tuning and reinforcement learning are difficult to configure under realistic compute budgets: the configuration space is hi…
PCL-Reasoner-V1.5: Advancing Math Reasoning with Offline Reinforcement Learning
Yao Lu, Dengdong Fan, Jianzheng Nie +4
We present PCL-Reasoner-V1.5, a 32-billion-parameter large language model (LLM) for mathematical reasoning. The model is built upon Qwen2.5-32B and refined via supervised fine-tuni…
AscendKernelGen: A Systematic Study of LLM-Based Kernel Generation for Neural Processing Units
Xinzi Cao, Jianyang Zhai, Pengfei Li +17
To meet the ever-increasing demand for computational efficiency, Neural Processing Units (NPUs) have become critical in modern AI infrastructure. However, unlocking their full pote…