6 papers
Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning
Songtao Tian, Guhan Chen, Bohan Li +2
Consistency distillation has significantly accelerated diffusion-model inference, but its sampling dynamics remain underexplored. We reveal an asymmetry: although Logit-Normal samp…
Mining or Synthesis? Rethinking Exploration Efficiency in Iterative Alignment of Mathematical Reasoning
Jun Rao, Zixiong Yu, Xuebo Liu +6
Iterative Direct Preference Optimization (DPO) has emerged as a widely used paradigm for aligning Large Language Models on reasoning tasks. Existing approaches typically rely on Be…
MathAgent: Adversarial Evolution of Constraint Graphs for Mathematical Reasoning Data Synthesis
Zixiong Yu, Jun Rao, Guhan Chen +5
Synthesizing high-quality mathematical reasoning data without human priors remains a significant challenge. Current approaches typically rely on seed data mutation or simple prompt…
On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains
Yicheng Li, Zixiong Yu, Guhan Chen +1
In this paper, we provide a strategy to determine the eigenvalue decay rate (EDR) of a large class of kernel functions defined on a general domain rather than . This…
Tool-Augmented Policy Optimization: Synergizing Reasoning and Adaptive Tool Use with Reinforcement Learning
Wenxun Wu, Yuanyang Li, Guhan Chen +2
Recent advances in large language models (LLMs) have popularized test-time scaling, where models generate additional reasoning tokens before producing final answers. These approach…
Divergence of Empirical Neural Tangent Kernel in Classification Problems
Zixiong Yu, Songtao Tian, Guhan Chen
This paper demonstrates that in classification problems, fully connected neural networks (FCNs) and residual neural networks (ResNets) cannot be approximated by kernel logistic reg…