11 papers · 1 filter
Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability
Xiao Liang, Zhong-Zhi Li, Zhenghao Lin +7
Large language models (LLMs) have demonstrated strong reasoning capabilities through step-by-step chain-of-thought (CoT) reasoning. Nevertheless, at the limits of model capability,…
Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR
Xiao Liang, Zhongzhi Li, Yeyun Gong +4
Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a key paradigm for post-training Large Language Models (LLMs), particularly for complex reasoning task…
Mixture of Neuron Experts
Runxi Cheng, Yuchen Guan, Yucheng Ding +6
In this work, we first explore whether the parameters activated by the MoE layer remain highly sparse at inference. We perform a sparsification study on several representative MoE…
Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
Liliang Ren, Yang Liu, Yadong Lu +3
Efficiently modeling sequences with infinite context length has long been a challenging problem. Previous approaches have either suffered from quadratic computational complexity or…
Rho-1: Not All Tokens Are What You Need
Zhenghao Lin, Zhibin Gou, Yeyun Gong +8
Previous language model pre-training methods have uniformly applied a next-token prediction loss to all training tokens. Challenging this norm, we posit that "9l training". Our ini…
Exploring the Mystery of Influential Data for Mathematical Reasoning
Xinzhe Ni, Yeyun Gong, Zhibin Gou +4
Selecting influential data for fine-tuning on downstream tasks is a key factor for both performance and computation efficiency. Recent works have shown that training with only limi…