arXiv subjects

Jinhui Yang

Publications and source records attributed to Jinhui Yang.

4 recordsLinked to original sources

arXiv2026

C2:Cross learning module enhanced decision transformer with Constraint-aware loss for auto-bidding

Decision Transformer (DT) shows promise for generative auto-bidding by capturing temporal dependencies, but suffers from two critical limitations: insufficient cross-correlation modeling among state, action, and return-to-go (RTG) sequences, and indiscriminate learning of optimal/suboptimal behaviors. To address these, we propose C2, a novel framework enhancing DT with two core innovations: (1) a Cross Learning Block (CLB) via cross-attention to strengthen inter-sequence correlation modeling; (2) a Constraint-aware Loss (CL) incorporating budget and Cost-Per-Acquisition (CPA) constraints for selective learning of optimal trajectories. Extensive offline evaluations on the AuctionNet dataset demonstrate consistent performance gains (up to 3.2% over state-of-the-art method) across diverse budget settings; ablation studies verify the complementary synergy of CLB and CL, confirming C2's superiority in auto-bidding. The code for reproducing our results is available at: https://github.com/Dingjinren/C2.

cs.LG↗

arXiv2025

An Improved High-order Adaptive Mesh Refinement Framework for Shock-turbulence Interaction Problems based on cell-centered finite difference schemes

This work presents a high-order finite-difference adaptive mesh refinement (AMR) framework for robust simulation of shock-turbulence interaction problems. A staggered-grid arrangement, in which solution points are stored at cell centers instead of at the vertices, is presented to address the boundary conservation issues encountered in previous studies. The key ingredient in the AMR framework, i.e., the high-order nonlinear interpolation method applied in the prolongation step together with the determination of fine-grid boundary conditions, are re-derived for staggered grids following the procedures in prior work [1] and are thus used here. Meanwhile, a high-order restriction method is developed in the present study as the coarse and fine grid solutions are non-collocated in this configuration. To avoid non-conservative interpolation at discontinuous cells that could incur instabilities, a hybrid interpolation strategy is proposed in this work for the first time, where the non-conservative WENO interpolation is applied in smooth regions whereas the second-order conservative interpolation is applied at shocks. This significantly mitigates the numerical instabilities introduced by non-conservative interpolation and pointwise replacement. The two interpolation approaches are seamlessly coupled through a troubled-cell detector achieved by a scale-irrelevant Riemann solver in a robust way. The present work is developed on a publicly available block-structured adaptive mesh refinement framework AMReX [2]. The canonical tests demonstrate that the proposed method is capable of accurately resolving a wide range of complex shock-turbulence interaction problems that have been proven intricate for existing approaches

physics.comp-ph↗

arXiv2022

Attention in Reasoning: Dataset, Analysis, and Modeling

While attention has been an increasingly popular component in deep neural networks to both interpret and boost the performance of models, little work has examined how attention progresses to accomplish a task and whether it is reasonable. In this work, we propose an Attention with Reasoning capability (AiR) framework that uses attention to understand and improve the process leading to task outcomes. We first define an evaluation metric based on a sequence of atomic reasoning operations, enabling a quantitative measurement of attention that considers the reasoning process. We then collect human eye-tracking and answer correctness data, and analyze various machine and human attention mechanisms on their reasoning capability and how they impact task performance. To improve the attention and reasoning ability of visual question answering models, we propose to supervise the learning of attention progressively along the reasoning process and to differentiate the correct and incorrect attention patterns. We demonstrate the effectiveness of the proposed framework in analyzing and modeling attention with better reasoning capability and task performance. The code and data are available at https://github.com/szzexpoi/AiR

cs.CV↗

arXiv2020

AiR: Attention with Reasoning Capability

While attention has been an increasingly popular component in deep neural networks to both interpret and boost performance of models, little work has examined how attention progresses to accomplish a task and whether it is reasonable. In this work, we propose an Attention with Reasoning capability (AiR) framework that uses attention to understand and improve the process leading to task outcomes. We first define an evaluation metric based on a sequence of atomic reasoning operations, enabling quantitative measurement of attention that considers the reasoning process. We then collect human eye-tracking and answer correctness data, and analyze various machine and human attentions on their reasoning capability and how they impact task performance. Furthermore, we propose a supervision method to jointly and progressively optimize attention, reasoning, and task performance so that models learn to look at regions of interests by following a reasoning process. We demonstrate the effectiveness of the proposed framework in analyzing and modeling attention with better reasoning capability and task performance. The code and data are available at https://github.com/szzexpoi/AiR

cs.CV↗