Accepted Papers

We have a total of 11 oral presentations scheduled, and all oral/poster papers must be presented at the poster session. Each oral presentation should consist of a 7-minute talk followed by a 2-minute Q/A period. Please note that, for poster papers, poster instructions will be released later.

  • Oral + Poster papers

    • 11:30 - 12:00 Noise Robust Graph Learning under Feature-Dependent Graph-Noise. pdf
    • 11:30 - 12:00 Data quality-based gradient optimization for recurrent neural networks. pdf
    • 11:30 - 12:00 GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation. pdf
    • 14:30 - 15:00 SubLIME: Less is More for LLM Evaluation. pdf
    • 14:30 - 15:00 CURATON: Clean Human Preference Data for Aligning LLMs. pdf
    • 14:30 - 15:00 Improving Embedding-Based Retrieval in Friend Recommendation with ANN Query Expansion. pdf
    • 15:30 - 16:15 LLMs and Physics Q&A: Improving Performance through Data Augmentation and Retrieval.
    • 15:30 - 16:15 Robust Data-centric Graph Structure Learning for Text Classification. pdf
    • 15:30 - 16:15 Could Small Language Models Serve as Recommenders? Towards Data-centric Cold-start Recommendations. pdf
    • 15:30 - 16:15 FASETS: Discovering Faceted Sets of Entities.
    • 15:30 - 16:15 RiskRAG: Automating Financial Risk Control with Retrieval-Augmented LLMs. pdf

  • Poster papers

    • Measuring the Predictability of Recommender Systems using Structural Complexity Metrics. pdf
    • Graph Coarsening via Convolution Matching for Scalable Graph Neural Network Training. pdf
    • CFinDEE: A Chinese Fine-Grained Financial Dataset for Document-Level Event Extraction. pdf
    • LLM-Guided Counterfactual Data Generation for Fairer AI.
    • Lighter Graph Convolutional Networks for Recommendation. pdf
    • Dynamic Tiling: A Model-Agnostic, Adaptive, Scalable, and Inference-Data-Centric Approach for Efficient and Accurate Small Object Detection.
    • Prompt Optimizer of Text-to-Image Diffusion Models for Abstract Concept Understanding. pdf
    • Benchmarking & Visualizing Social Graph Unlearning.