From the research desk.

[CollaborateCom-26] our work on “From Training to Inference: Collaborative Signal-Driven Mitigation of Dual Inconsistencies in Generative Recommendation” has been accepted.

[KDD-26] our work on “A Scaling-Friendly Dual-Stack Architecture for Cross-Domain Conversion Rate Modeling: The 2nd Place of KDD Cup 2026” has been accepted.

[KDD-26] our work on “Revisiting Graph Autoencoders as Implicit Contrastive Learners” has been accepted.

[KDD-26] our work on “One For All: Achieving Adaptive Graph Neural Networks via Mixture of Message Passing” has been accepted.

[TKDE-25] our work on “SaGIF: Improving Individual Fairness in Graph Neural Networks via Similarity Encoding” has been accepted.

[AAAI-26] our work on “GT-SNT: A Linear-Time Transformer for Large-Scale Graphs via Spiking Node Tokenization” has been accepted.

[Knowledge-Based Systems] our work on “Capturing Latent Evolution in Dynamic Graph: A Dual-view Architecture from Spectral Perspective” has been accepted.

[TPAMI-25] our work on “Heterophily-aware Representation Learning on Heterogenerous Graphs” has been accepted.

[Knowledge-Based Systems] our work on “FairDLA: Improving the fairness-utility trade-off in graph neural netwo via dual-level alignment” has been accepted.

[ICML-25] our work on “Measuring Diversity in Synthetic Datasets” has been accepted.

[ICML-25] our work on “Improving Conversational Capabilities of Speech Language Models via Generative Dual-channel Spoken Dialogue Learning” has been accepted.

[Knowledge-Based Systems] our work on “Long-term evolutionary patterns matter: Self-supervised anomaly detection on dynamic graphs” has been accepted.

[NeurIPS-2024 Workshop on Audio Imagination] our work on “Parrot: Autoregressive Spoken Dialogue Language Modeling with Decoder-only Transformers” has been accepted.

[NeurIPS-2024] our work on “State Space Models on Temporal Graphs: A First-Principles Study” has been accepted.

[KDD-24] our work on “One Fits All: Learning Fair Graph Neural Networks for Various Sensitive Attributes” has been accepted.

[KDD-24] our collaboration with Ant Group on “Revisiting Modularity Maximization for Graph Clustering: A Contrastive Learning Perspective” has been accepted.

[ACL-24] our collaboration with Tencent on “Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm” has been accepted.

[ICML-24] our collaboration with HKUST and Tencent on “Parameter-Efficient Fine-Tuning with Discrete Fourier Transform” has been accepted.

[TCSS] our work on “FairAGG: Towards Fair Graph Neural Networks via Fair Aggregation” has been accepted.

[TCSS] our work on “A Review-level Sentiment Information Enhanced Multi-task Learning Approach for Explainable Recommendation” has been accepted.

[WWW-24] our work on “Fair Graph Representation Learning via Sensitive Attribute Disentanglement” has been accepted.

[ICLR-24] our work on “A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks” has been accepted.