Yu Wang

End-to-End Fairness Optimization with Fair Decision-Focused Learning

Yu Wang, Violet, Chen

Many real-world systems rely on predictive models to inform decisions, and fairness concerns arise in both the prediction and decision stages. We introduce end-to-end fairness optimization (E2EFO) as a unifying framework that integrates fairness across the prediction-to-decision…Read more

From Static to Dynamic: Evaluating the Impact of Temporal Bias in Historical Street View Images for Cross‐View Geolocalization

Yu Wang, Ana Basiri

ABSTRACT Street View Images (SVIs) have become a valuable source of geotagged visual data, increasingly used in tasks such as assessing socioeconomic conditions, mapping accessibility, monitoring infrastructure, and supporting navigation and perception studies. However, while the…Read more

Rethinking Multi-Branch and Cross-Backbone Fusion for Vehicle Re-Identification in the Foundation-Model Era

Yu Wang, Hongyu Yang

Multi-branch architectures and CNN-Transformer fusion have long been regarded as effective ways to improve vehicle re-identification (Re-ID) by combining complementary representations. In this work, we revisit this assumption in the foundation-model era through a comprehensive em…Read more

The Dark Room in the Reward Channel: Dense Prediction Rewards Collapse GRPO-Trained LLM Agents -- and What Actually Works

Yu Wang

Dense per-step supervision is an appealing remedy for sparse-reward, long-horizon LLM agents: reward the agent for predicting its next observation, and memory should follow. We show that under group-normalized RL (GRPO), this recipe does not merely fail -- it destroys the policy.…Read more

DAIS: Dependency-Aware Intermediate QA Supervision for Complex Reasoning

Yu Wang, Ming Fan, Xicheng Zhang, Zhiyong Li, Zhihu Wang, Caiyue Xu, et al.

Chain-of-thought (CoT) supervision exposes intermediate rationales, but flat rationale targets usually optimize a single reasoning sequence and provide limited supervision on how local conclusions should support later decisions. We introduce Dependency-Aware Intermediate QA Super…Read more

Reward-Free Evolving Agents via Pairwise Validator

Minghao Liu, Yu Wang, Jiayun Wang, Wei Wei

A self-evolving agentic loop repeatedly proposes a tweaked version of an agent (its prompt template or program) and accepts or rejects the change based on a per-iteration quality signal. Designing that signal is often the costly part of the project: a reliable scalar reward requi…Read more

Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents

Yixian Zhang, Huanming Zhang, Feng Gao, Xiao Li, Zhihao Liu, Chunyang Zhu, et al.

Language-conditioned manipulation requires both precise contact-rich control and robust reasoning over language, scenes, and long horizons. End-to-end Vision-Language-Action (VLA) models provide strong local visuomotor skills, but they are trained on in-distribution task trajecto…Read more

Multimodal 3D LUT Generation via StatLUT with Statistical Features for Photorealistic Style Transfer

Yifan Wang, Zhixiang Hao, Yu Wang, Congchao Zhu

Photorealistic Style Transfer (PST) aims to transfer the color and tonal style of a reference to a content image while strictly preserving its structural integrity. However, existing deep learning-based methods inherently suffer from semantic entanglement caused by pre-trained im…Read more

Infinity-Parser2 Technical Report

Zuming Huang, Jun Huang, Kexuan Ren, Baode Wang, Weizhen Li, Jianming Feng, et al.

We present Infinity-Parser2, a large multimodal model that couples a controllable data-synthesis pipeline with multi-task reinforcement learning for end-to-end document parsing, addressing the persistent scarcity of faithfully annotated parsing corpora. Our contributions are thre…Read more

Enhancing the Forecasting Capability of Multi-Model Blending Algorithms for Extreme Precipitation via Joint Use of Station and Gridded Observations

Yu Wang, Yong Cao, Kan Dai, Yue Shen, Xiaoqing Zeng, Ruixia Zhao

Accurate extreme precipitation forecasting is critical for disaster mitigation but remains challenging for numerical weather prediction (NWP) models due to systemic intensity underestimation and spatial displacement. Traditional precipitation multi-model blending algorithms perfo…Read more

STEAM: Self-Supervised Temporal Ensemble Advantage Modeling for Real-World Robot Learning

Zhihao Liu, Qiuyi Gu, Yitao Wang, Dongming Qiao, Yixian Zhang, Shuaihang Chen, et al.

Real-world robot learning increasingly relies on heterogeneous data, but demonstrations and rollouts often mix useful progress with stalls, corrections, and suboptimal behavior. Effective policy learning therefore requires frame-level advantages that distinguish reliable local pr…Read more

Benchmarking Multi-Modal Graph-based Social Media Popularity Prediction

Utkarsh Sahu, Zhisheng Qi, Li Zhu, Yizhao Yang, Jun Li, Ryan Rossi, et al.

Social media popularity prediction aims to forecast the future reach or influence of online content from early-stage observations. Accurate prediction enables key downstream applications, such as advertising optimization and strategic content planning by users, creators, and plat…Read more

Multi-Band-Image Based Detection of Apple Surface Defect Using Machine Vision and Deep Learning

Yan Tang, Hongyi Bai, Laijun Sun, Yu Wang, Jingli Hou, Yonglong Huo, et al.

Accurate surface defect extraction of apples is critical for their quality inspection and marketing purposes. Using multi-band images, this study proposes a detection method for apple surface defects with a combination of machine vision and deep learning. Five single bands, 460,…Read more

Machine learning prediction of tungsten grain boundary mechanics for fusion applications

Yu Wang, Liuming Wei, C. Zhang, Zhi Zeng