7 papers
Learning to Adapt SFT Data for Better Reasoning Generalization
Lisong Sun, Li Wang, Chen Zhang +4
Large language models (LLMs) have achieved remarkable progress, with post-training playing a crucial role in enhancing their reasoning capabilities. Among post-training paradigms,…
When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards
Li Wang, Xiaodong Lu, Xiaohan Wang +5
Large Language Models (LLMs) have achieved remarkable advancements in reasoning capabilities empowered by Reinforcement Learning with Verifiable Rewards (RLVR). Nonetheless, RLVR i…
TSFLora: Token-Compressed Split Fine-Tuning for Wireless Edge Networks
Xianke Qiang, Zheng Chang, Li Wang +1
Adapting large AI models (LAMs) to personalized edge data is challenging because wireless devices have limited memory, computation, and uplink capacity. Federated fine-tuning prese…
TAMTRL: Teacher-Aligned Reward Reshaping for Multi-Turn Reinforcement Learning in Long-Context Compression
Li Wang, Yandong Wang, Xin Yu +3
The rapid progress of large language models (LLMs) has led to remarkable performance gains across a wide range of tasks. However, when handling long documents that exceed the model…
Decoupling Understanding from Reasoning via Problem Space Mapping for Small-Scale Model Reasoning
Li Wang, Changhao Zhang, Zengqi Xiu +4
Despite recent advances in the reasoning capabilities of Large Language Models (LLMs), improving the reasoning ability of Small Language Models (SLMs, e.g., up to 1.5B parameters)…
An Investigation of Batch Normalization in Off-Policy Actor-Critic Algorithms
Li Wang, Sudun, Xingjian Zhang +2
Batch Normalization (BN) has played a pivotal role in the success of deep learning by improving training stability, mitigating overfitting, and enabling more effective optimization…