Xiao Han

Entity embeddings outperform traditional encoding methods in high-cardinality fraud detection, achieving a record AUC-ROC score that could redefine best practices in the field.

Early behavioral indicators can drastically improve churn prediction, but their effectiveness hinges on cohort design and feature selection.

Comparison-based supervision can drastically enhance reasoning quality in medical AI, outperforming traditional reward systems.

Achieving superior accuracy-efficiency trade-offs, ParetoPO redefines how tool-integrated agents can be optimized for real-world applications.

Stop relying on LLMs to "hallucinate" reasoning paths – SEARCH-R uses a fine-tuned Llama3.1-8B model and dependency tree-based retrieval to navigate multi-hop question answering more reliably.

LLMs can generate better features from tabular data when deployed as a multi-agent system with explicit memory of past procedures, feedback, and concepts.

Achieve an 8x speedup in chest X-ray report generation without sacrificing clinical accuracy by distilling multi-step diffusion into a single, efficient step.

Forget independent feature extraction: a new architecture uses LVLMs to explicitly model the relationships between drone and satellite imagery, substantially boosting geolocalization accuracy.

Imagine designing custom fonts simply by describing them or providing a reference image – VecGlypher makes it a reality by directly generating editable vector glyphs with a single multimodal language model.