arXiv subjects

Yuchen Ge

Publications and source records attributed to Yuchen Ge.

7 recordsLinked to original sources

arXiv2026

From Absolute to Relative: Rethinking Reward Shaping in Group-Based Reinforcement Learning

Reinforcement learning has become a cornerstone for enhancing the reasoning capabilities of Large Language Models, where group-based approaches such as GRPO have emerged as efficient paradigms that optimize policies by leveraging intra-group performance differences. However, these methods typically rely on absolute numerical rewards, introducing intrinsic limitations. In verifiable tasks, identical group evaluations often result in sparse supervision, while in open-ended scenarios, the score range instability of reward models undermines advantage estimation based on group means. To address these limitations, we propose Reinforcement Learning with Relative Rewards (RLRR), a framework that shifts reward shaping from absolute scoring to relative ranking. Complementing this framework, we introduce the Ranking Reward Model, a listwise preference model tailored for group-based optimization to directly generate relative rankings. By transforming raw evaluations into robust relative signals, RLRR effectively mitigates signal sparsity and reward instability. Experimental results demonstrate that RLRR yields consistent performance improvements over standard group-based baselines across reasoning benchmarks and open-ended generation tasks.

cs.LG↗

arXiv2025

Boundary layer transition induced by surface roughness distributed over a low-pressure turbine blade

Direct numerical simulations of a low-pressure turbine with roughness elements distributed over the blade surface have been performed. A series of fifteen cases with varying roughness heights and streamwise wavenumbers are introduced to present a systematic study of the effect of roughness on the various transition phenomena in the suction-side boundary layer. For cases with large roughness heights, the boundary layer is violently disturbed by the wake of rough elements in the leading edge (LE) region, and maintains the turbulent state over the whole blade suction-side. For cases with small roughness heights, however, the disturbances induced by the LE roughness are suppressed by the favourable pressure gradient in the downstream boundary layer, and the relaminarized flow does not undergo transition until the separation near the blade trailing edge (TE). Furthermore, the streamwise wavenumber of the distributed roughness plays an important role in cases with intermediate roughness height. Specifically, cases with larger streamwise slope show earlier transition induced by strong shear layer instability, which manages to suppress the mean flow separation near the TE region. Overall, the combined effect of several factors, including the geometric effect at the blade LE and TE, the complex pressure gradient distribution across the turbine vane, and the various roughness configurations, is responsible for the intriguing boundary layer behaviours in the present study.

physics.flu-dyn↗

arXiv2025

Constructing wall turbulence using hierarchical hairpin vortices

Wall-bounded turbulence is characterized by coherent, worm-like structures such as hairpin vortices. The attached-eddy model provides a successful statistical framework for the log-law region, yet the complex geometry and multiscale nature of wall-turbulence vortices remain challenging for physics-based modelling. Here, we model wall turbulence as an ensemble of complex vortices, introducing a systematic approach to constructing turbulence fields enriched with hierarchically organized hairpin vortex packets. The geometry and organization of the vortex packets are calibrated to match observations, enabling the model to reproduce both attached and detached motions through a height-dependent core-size variation. Our model successfully reproduces the key statistical and structural features of wall turbulence, matching direct numerical simulations of turbulent channel flow at friction Reynolds numbers from 1,000 to 10,000. More importantly, it also reveals new insights into the coherent structures, emphasizing the role of vortex geometry, packet organization, and hierarchy in setting the attached/detached balance, meandering streaks and inclination angles, superstructure alignment, and the overall partition of contributions. Moreover, the constructed channel turbulence rapidly transitions into fully developed turbulence in direct numerical simulation, demonstrating its physical self-consistency and practical utility for initializing high-fidelity simulations. This approach significantly reduces computational costs associated with turbulence development while providing a flexible framework for testing and advancing turbulence models based on vortex structures.

physics.flu-dyn↗

arXiv2025

Asymmetric Decision-Making in Online Knowledge Distillation:Unifying Consensus and Divergence

Online Knowledge Distillation (OKD) methods streamline the distillation training process into a single stage, eliminating the need for knowledge transfer from a pretrained teacher network to a more compact student network. This paper presents an innovative approach to leverage intermediate spatial representations. Our analysis of the intermediate features from both teacher and student models reveals two pivotal insights: (1) the similar features between students and teachers are predominantly focused on foreground objects. (2) teacher models emphasize foreground objects more than students. Building on these findings, we propose Asymmetric Decision-Making (ADM) to enhance feature consensus learning for student models while continuously promoting feature diversity in teacher models. Specifically, Consensus Learning for student models prioritizes spatial features with high consensus relative to teacher models. Conversely, Divergence Learning for teacher models highlights spatial features with lower similarity compared to student models, indicating superior performance by teacher models in these regions. Consequently, ADM facilitates the student models to catch up with the feature learning process of the teacher models. Extensive experiments demonstrate that ADM consistently surpasses existing OKD methods across various online knowledge distillation settings and also achieves superior results when applied to offline knowledge distillation, semantic segmentation and diffusion distillation tasks.

cs.CV↗

arXiv2023

Gr\"obner and Graver bases for calculating Opportunity Cost Matrices

Opportunity cost matrices are interesting in the context of scenario reduction. We provide new algorithms, based on ideas from algebraic geometry, to efficiently compute the opportunity cost matrix using computational algebraic geometry. We demonstrate the efficacy of our algorithms by computing opportunity cost matrices for two stochastic integer programs.

math.OC↗

arXiv2021

Bid Optimization using Maximum Entropy Reinforcement Learning

Real-time bidding (RTB) has become a critical way of online advertising. In RTB, an advertiser can participate in bidding ad impressions to display its advertisements. The advertiser determines every impression's bidding price according to its bidding strategy. Therefore, a good bidding strategy can help advertisers improve cost efficiency. This paper focuses on optimizing a single advertiser's bidding strategy using reinforcement learning (RL) in RTB. Unfortunately, it is challenging to optimize the bidding strategy through RL at the granularity of impression due to the highly dynamic nature of the RTB environment. In this paper, we first utilize a widely accepted linear bidding function to compute every impression's base price and optimize it by a mutable adjustment factor derived from the RTB auction environment, to avoid optimizing every impression's bidding price directly. Specifically, we use the maximum entropy RL algorithm (Soft Actor-Critic) to optimize the adjustment factor generation policy at the impression-grained level. Finally, the empirical study on a public dataset demonstrates that the proposed bidding strategy has superior performance compared with the baselines.

cs.LG↗

arXiv2021

Orderly Dual-Teacher Knowledge Distillation for Lightweight Human Pose Estimation

Although deep convolution neural networks (DCNN) have achieved excellent performance in human pose estimation, these networks often have a large number of parameters and computations, leading to the slow inference speed. For this issue, an effective solution is knowledge distillation, which transfers knowledge from a large pre-trained network (teacher) to a small network (student). However, there are some defects in the existing approaches: (I) Only a single teacher is adopted, neglecting the potential that a student can learn from multiple teachers. (II) The human segmentation mask can be regarded as additional prior information to restrict the location of keypoints, which is never utilized. (III) A student with a small number of parameters cannot fully imitate heatmaps provided by datasets and teachers. (IV) There exists noise in heatmaps generated by teachers, which causes model degradation. To overcome these defects, we propose an orderly dual-teacher knowledge distillation (ODKD) framework, which consists of two teachers with different capabilities. Specifically, the weaker one (primary teacher, PT) is used to teach keypoints information, the stronger one (senior teacher, ST) is utilized to transfer segmentation and keypoints information by adding the human segmentation mask. Taking dual-teacher together, an orderly learning strategy is proposed to promote knowledge absorbability. Moreover, we employ a binarization operation which further improves the learning ability of the student and reduces noise in heatmaps. Experimental results on COCO and OCHuman keypoints datasets show that our proposed ODKD can improve the performance of different lightweight models by a large margin, and HRNet-W16 equipped with ODKD achieves state-of-the-art performance for lightweight human pose estimation.

cs.CV↗