4 citations · 4 across the 4 of their papers we have counts for
5 papers
HART: Hybrid Attention-RWKV Time series Foundation Model
Qingwen Lin, Boyan Xu, Shifeng Xie +3
Non-autoregressive multi-step forecasting (NAF) enables time series foundation models to predict an entire future horizon in a single forward pass. Despite its strong sequence mode…
SANE: State Anomaly Neutralization for Stable Extreme-Context Delta-Rule Models
Qingwen Lin, Boyan Xu, Xiao Liu +2
Delta-Rule recurrent models maintain a fixed-size state, enabling inference memory but potentially becoming unstable under extreme-context extrapolation. By tracking RWKV-7…
ENTRA: Entropy-Based Redundancy Avoidance in Large Language Model Reasoning
Ruichu Cai, Haopeng Du, Qingwen Lin +3
Large Reasoning Models (LRMs) often suffer from overthinking, generating unnecessarily long reasoning chains even for simple tasks. This leads to substantial computational overhead…
CMCTS: A Constrained Monte Carlo Tree Search Framework for Mathematical Reasoning in Large Language Model
Qingwen Lin, Boyan Xu, Guimin Hu +4
This paper introduces the Constrained Monte Carlo Tree Search (CMCTS) framework to enhance the mathematical reasoning capabilities of Large Language Models (LLM). By incorporating…
From Large to Tiny: Distilling and Refining Mathematical Expertise for Math Word Problems with Weakly Supervision
Qingwen Lin, Boyan Xu, Zhengting Huang +1
Addressing the challenge of high annotation costs in solving Math Word Problems (MWPs) through full supervision with intermediate equations, recent works have proposed weakly super…