5 papers
Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning
Shuyao Xu, Cheng Peng, Jiangxuan Long +3
Recent advances in model distillation show that data from advanced reasoning models can effectively train smaller student models. However, standard practices discard incorrect reas…
Theoretical Foundation of Flow-Based Time Series Generation: Provable Approximation, Generalization, and Efficiency
Jiangxuan Long, Zhao Song, Chiwun Yang
Recent studies suggest utilizing generative models instead of traditional auto-regressive algorithms for time series forecasting (TSF) tasks. These non-auto-regressive approaches i…
Theoretical Guarantees for High Order Trajectory Refinement in Generative Flows
Chengyue Gong, Xiaoyu Li, Yingyu Liang +4
Flow matching has emerged as a powerful framework for generative modeling, offering computational advantages over diffusion models by leveraging deterministic Ordinary Differential…
Neural Algorithmic Reasoning for Hypergraphs with Looped Transformers
Zekai Huang, Yingyu Liang, Zhenmei Shi +2
Looped Transformers have shown exceptional neural algorithmic reasoning capability in simulating traditional graph algorithms, but their application to more complex structures like…
Circuit Complexity Bounds for RoPE-based Transformer Architecture
Bo Chen, Xiaoyu Li, Yingyu Liang +3
Characterizing the express power of the Transformer architecture is critical to understanding its capacity limits and scaling law. Recent works provide the circuit complexity bound…