Jiandong Ding (丁建栋)

Research Focus

I am an AI Architecture Expert & Senior Algorithm Expert at Huawei Technologies, bridging the gap between theoretical algorithms and industrial-scale systems.

My research philosophy is summarized as "From Biological Sequences to User Behaviors". I apply deep representation learning to decipher underlying patterns in data—from genomic sequences in my early career to billion-scale user behavior logs in commercial recommendation systems today.

Currently, I focus on building Next-Generation Recommender Systems driven by Generative AI, with specific interests in:

Generative RecSys: LLM-driven Recommendation, Sequential Modeling, and User Representation.
Trustworthy AI: Causal Inference, Unbiased Learning, and Fairness in Ranking.
System Efficiency: Edge-Cloud Collaboration, Retrieval Architecture, and Model Compression.

🔥 News

[Mar 2026] ✈️ Attending ECIR 2026 in the Netherlands. Looking forward to deep academic exchanges!
[Mar 2026] 🎉 Paper "Mitigating Popularity Bias in Recommendation" accepted by ACM TOIS.
[Jan 2026] 🚀 Paper "Hierarchical and Preference-Aware Generative Recommendations" accepted by TheWebConf (WWW) 2026.
[Nov 2025] Two papers accepted! "RPE4Rec" by WSDM 2026, and "Invariant Feature Learning" by AAAI 2026.

🎯 Research Highlights

My current research focuses on three core pillars: Generative & Trustworthy RecSys, Extreme Efficiency, and LLM Agents.

1. Next-Gen Recommendation: Generative & Trustworthy

[WWW 2026] Generative Recs: Hierarchical & Preference-Aware Problem Existing "flat-sequence" generative models overlook the hierarchical structure of user sessions and introduce noise in long histories.

Breakthrough Proposes a two-stage generative framework that shatters the traditional "flat sequence" assumption, accurately capturing long- and short-term structured interests through hierarchical preference awareness and sparse attention.

[AAAI 2026] Causal Inference for Watch-time Prediction Problem In short-video feeds, "duration biases" (longer videos naturally get more watch time) mislead algorithms.

Breakthrough Proposes a Duration-Invariant Feature Learning (DIFL) framework based on causal inference to eliminate duration bias in video recommendation, utilizing kernel-based regularization to isolate genuine user interests for highly accurate counterfactual watch-time prediction.

2. Extreme Efficiency at Scale

[WSDM 2026] RPE4Rec: High-Efficiency Dynamic Retrieval Problem Advanced Transformers are often too slow for real-time retrieval on billion-scale items.

Breakthrough Introduces an Efficient Relative Position Encoding (RPE) architecture that eliminates the latency bottlenecks of heavy Transformers, achieving sub-millisecond real-time retrieval on billion-scale dynamic graphs.

[KDD 2024] Low-Rank Compression for CTR Prediction Breakthrough Presents a unified low-rank compression framework that reduces massive Embedding memory consumption by over 80%, unlocking high-performance recommendation in resource-constrained environments like on-device deployment.

3. LLM Agents & Data Intelligence

[ICSOC 2025] NL2SQL Benchmark for Business Intelligence Intelligence Layer Bridges the gap between academia and industry by introducing the first natural language to SQL (NL2SQL) service evaluation benchmark specifically designed for real-world, enterprise-level Business Intelligence (BI) scenarios.

[NeurIPS 2021] DP-SSL: Robust Semi-supervised Learning Problem Deep learning performance heavily relies on massive labeled data, which is expensive to obtain.

Breakthrough Ingeniously fuses Data Programming with Semi-Supervised Learning to overcome model collapse in extremely low-resource settings, achieving highly robust classification performance with only single-digit labeled samples.

📫 Get in Touch

I am deeply committed to bridging the gap between academia and industry. Having led numerous research initiatives at Huawei CBG and Alibaba DAMO, I am always open to:

Academic Partnerships: Collaborative research & grant applications.
Professional Events: Industry summits and tech forums.

For collaboration inquiries: jdding [at] fudan.edu.cn