5 papers · 1 filter
When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoning
Wang Yang, Shouren Wang, Chaoda Song +6
Group Relative Policy Optimization (GRPO) has become a key technique for improving reasoning abilities in large language models, yet its behavior under different domain sequencing…
Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?
Shouren Wang, Wang Yang, Xianxuan Long +3
Hybrid thinking enables LLMs to switch between reasoning and direct answering, offering a balance between efficiency and reasoning capability. Yet our experiments reveal that curre…
MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper
Runjia Zeng, Guangyan Sun, Qifan Wang +8
Considering deep neural networks as manifold mappers, the pretrain-then-fine-tune paradigm can be interpreted as a two-stage process: pretrain establishes a broad knowledge base, a…
Thinking Preference Optimization
Wang Yang, Hongye Jin, Jingfeng Yang +2
Supervised Fine-Tuning (SFT) has been a go-to and effective method for enhancing long chain-of-thought (CoT) reasoning in relatively small LLMs by fine-tuning them with long CoT re…
Quantize What Counts: More for Keys, Less for Values
Mohsen Hariri, Alan Luo, Weicong Chen +6
Large Language Models (LLMs) suffer inference-time memory bottlenecks dominated by the attention Key-Value (KV) cache, which scales with model size and context length. While KV-cac…