The 2026 China University Computer Competition's Big Data Challenge revealed the monthly star award winners, each receiving a prize, and the top teams detailed their feature engineering, model selection, training validation, and portfolio combination tactics that led to their success.
The 2026 China University Computer Competition – Big Data Challenge reveals the Monthly Star award winners, each receiving 800 RMB, and presents detailed experience reports from the top teams covering feature engineering, model selection, training validation, and ensemble strategies for stock prediction.
UI‑Venus‑1.5, an open‑source end‑to‑end GUI agent from Ant Group, tackles knowledge gaps, offline‑online mismatch, and high coordination costs by introducing mid‑stage training with a 10 B‑token corpus, online reinforcement learning, a “split‑then‑merge” model fusion, and a scalable DaaS layer, achieving top scores on VenusBench‑GD, ScreenSpot‑Pro and real‑world AndroidWorld tests.
Mistral AI’s newly released Small 4 model merges the capabilities of its three flagship models into a more efficient architecture, and its entry into Nvidia’s Nemotron alliance marks a strategic shift toward an open‑source AI ecosystem that could challenge the dominance of closed‑source giants like OpenAI and Google.
A small tech firm, tngtech, released an open‑source model fusion called DeepSeek‑R1T‑Chimera that merges R1 inference with V3‑0324 without fine‑tuning, distillation, or prompts, achieving the same intelligence as R1 while reducing token output by 40% and speeding up inference.
This article examines why ensemble methods are crucial for large language models, outlines five core fusion strategies—including model integration, probability integration, graft learning, crowdsourced voting, and Mixture of Experts—provides implementation details, pseudo‑code, and discusses practical challenges and recent research advances.
This article explores how large language models can be incorporated into recommender systems, discussing background challenges, specific integration points across the recommendation pipeline, practical implementation methods, experimental results, and future research directions, while highlighting industrial considerations and potential improvements.
DeWu Community’s recommendation system progressed from single‑objective CTR modeling to a multi‑objective framework that combines independent models for dwell time, video completion and user interactions via score‑fusion, ranking‑learning and multi‑task architectures with shared parameters and gradient‑blocking, delivering higher engagement and retention.
iQIYI improves short‑video recommendation by applying multi‑objective optimization—weighting clicks by watch duration, fusing separate click and watch‑time models, employing multi‑task learning with ESMM/MMOE and Pareto‑guided PSO hyper‑parameter search—delivering 7%+ watch‑time growth, 20%+ interaction gains, and 1.5‑3% CTR lifts while planning cross‑scene learning and further model refinements.
The article describes how NetEase adapts a pre‑trained BERT model to classify news articles into ultra‑short, short, or long timeliness categories by combining rule‑based strong and weak time cues, key‑sentence extraction, domain‑embedding fusion and multi‑layer semantic aggregation, achieving accurate and interpretable predictions for its platform.
This article describes how 58.com’s AI Lab built and continuously improved the QABot intelligent customer‑service system by designing classification and retrieval models, evaluating FastText, LSTM‑DSSM, BERT and a self‑developed SPTM framework, and finally fusing them to boost answer rates and user experience.
In this interview, DYG team member Wang He introduces his teammates, explains why they formed the team, and shares detailed model‑fusion techniques—including input variation, diverse model architectures, and training‑target differences—to boost competition scores during the final stage.
The article presents qa_match, a TensorFlow‑based open‑source QA matching system that combines BiLSTM‑attention domain classification with DSSM intent matching, explains its architecture, training workflow, features, future roadmap, and how developers can contribute to the project.
The article details the Travel team's award‑winning solution for the WSDM Cup 2019 fake‑news detection task, describing data analysis, preprocessing, label‑propagation augmentation, a BERT‑based baseline, a three‑stage multi‑level model‑fusion framework, experimental results, and future directions.
The WitcheR team won the 2018 iQIYI multimodal video person identification challenge by building a fast pipeline that combined a custom face‑and‑keypoint detector, ArcFace‑trained face embeddings, scene classification, and a three‑layer MLP with several training tricks, achieving a final mAP of 88.6 % and demonstrating the value of rapid idea validation and open‑sourced code for future challenges.
In the WSDM Cup 2019 fake-news detection challenge, the Meituan Travel team secured second place by combining extensive data analysis, Chinese-English BERT fine-tuning, label-propagation augmentation, and a three-level fusion framework—blending, stacking, and linear regression—that lifted weighted accuracy to 0.88156.
The article presents a comprehensive overview of how Shumei Technology leverages machine learning—including supervised, unsupervised, and reinforcement learning methods—across its credit scoring, fraud detection, advertising, and audio content moderation services, highlighting practical challenges, model fusion techniques, and future research directions.
The article shares a Beijing University team's experience in the first Tencent Social Advertising algorithm contest, detailing their fourth‑place finish, best‑presentation award, and five key strategies—including business‑logic analysis, model innovation, multi‑model fusion, teamwork, and leveraging existing research—to improve conversion‑rate prediction performance.
The presentation introduces JD's Data Model Component Management Platform, detailing its four core functions—risk control, effect evaluation, model fusion, and multi‑scenario application—while explaining how these capabilities improve model reliability, commercial value, and operational efficiency across numerous business products.
The nju_newbiew team, winners of the weekly champion in Tencent Social Ads University Algorithm Competition, recount their data processing, offline validation, feature engineering, and model strategies, highlighting practical machine‑learning lessons while also providing competition announcements and contact information.
This article explains how to predict customer churn by analyzing competition data, extracting and engineering features, applying GBDT‑based XGBoost models, tuning hyper‑parameters, and improving performance through bagging and stacking model fusion techniques.
This article presents how deep learning techniques are applied to Sogou's mobile search advertising, detailing the system architecture, feature design, multi‑model fusion strategies, engineering implementation, evaluation metrics, and future directions for improving CTR prediction performance.
