Selected work

Representative Papers

Bridging the Semantic-Collaborative Gap: An Asymmetric Graph Architecture for Cold-Start Item Recommendation

Jun 04, 2026

This work addresses the cold-start problem for both new content and new devices in recommender systems by formulating it as an inductive graph completion task on a temporal bipartite device–content graph. The authors propose an asymmetric graph architecture: the device tower captures collaborative signals through message passing over viewing histories, while the content tower generates embeddings solely from intrinsic semantic features, without relying on item IDs or interaction data. A Shallow-RHS design maps content semantics into a collaborative-aware embedding space. The approach is further extended to device cold-start by leveraging demographic features to construct cohort embeddings for implicit graph completion. Integrated with approximate nearest neighbor retrieval, the system enables real-time embedding generation and candidate recall. Large-scale online experiments demonstrate significant improvements in user engagement, content exposure, ramp-up speed for new content, and key metrics for new devices.

0 citationsRead paper

Revealing Interpretable Failure Modes of VLMs

May 12, 2026

This work addresses the critical yet underexplored problem of hidden, high-risk failures in vision-language models (VLMs) within safety-critical scenarios, where systematic and interpretable failure identification methods are lacking. The authors propose REVELIO, a novel framework that, for the first time, models VLM failures as interpretable combinations of semantic concepts—such as pedestrian distance or adverse weather conditions—and introduces a diversity-aware beam search coupled with Gaussian process Thompson sampling to efficiently navigate the exponentially large combinatorial space. Evaluated in autonomous driving and indoor robotics simulation environments, REVELIO uncovers previously unreported structural vulnerabilities, including spatial mislocalization, obstacle neglect, and erroneous safety hazard alerts, thereby providing actionable insights for enhancing VLM reliability and safety.

0 citationsRead paper

RelBench v2: A Large-Scale Benchmark and Repository for Relational Data

Feb 13, 2026

Relational deep learning (RDL) has emerged as a powerful paradigm for learning directly on relational databases by modeling entities and their relationships across multiple interconnected tables. As this paradigm evolves toward larger models and relational foundation models, scalable and realistic benchmarks are essential for enabling systematic evaluation and progress. In this paper, we introduce RelBench v2, a major expansion of the RelBench benchmark for RDL. RelBench v2 adds four large-scale relational datasets spanning scholarly publications, enterprise resource planning, consumer platforms, and clinical records, increasing the benchmark to 11 datasets comprising over 22 million rows across 29 tables. We further introduce autocomplete tasks, a new class of predictive objectives that require models to infer missing attribute values directly within relational tables while respecting temporal constraints, expanding beyond traditional forecasting tasks constructed via SQL queries. In addition, RelBench v2 expands beyond its native datasets by integrating external benchmarks and evaluation frameworks: we translate event streams from the Temporal Graph Benchmark into relational schemas for unified relational-temporal evaluation, interface with ReDeLEx to provide uniform access to 70+ real-world databases suitable for pretraining, and incorporate 4DBInfer datasets and tasks to broaden multi-table prediction coverage. Experimental results demonstrate that RDL models consistently outperform single-table baselines across autocomplete, forecasting, and recommendation tasks, highlighting the importance of modeling relational structure explicitly.

0 citationsRead paper

Predictive Query Language: A Domain-Specific Language for Predictive Modeling on Relational Databases

Feb 10, 2026

This work addresses the cumbersome and error-prone process of manually extracting samples and labels from relational databases for traditional machine learning modeling. To streamline this workflow, the authors propose PQL, a declarative domain-specific language inspired by SQL that enables users to define diverse predictive tasks—including regression, classification, time-series forecasting, and recommendation—through a single query directly over relational databases, with training labels automatically generated. PQL offers two implementations: one optimized for low-latency, small-scale scenarios and another designed for large-scale data processing. The approach has been validated in real-world applications such as financial fraud detection, product recommendation, and load forecasting, demonstrating its versatility, efficiency, and significant improvements in modeling productivity and scalability.

0 citationsRead paper

PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models

Feb 03, 2026

This work addresses the scarcity of publicly available multi-table relational databases for training Relational Foundation Models (RFMs) due to privacy constraints. To overcome this limitation, the authors propose PluRel, a novel framework that, for the first time, models database schemas as directed graphs and captures primary–foreign key relationships via bipartite graphs, integrating a conditional causal mechanism to generate structurally coherent and diverse synthetic multi-table data. The approach is lightweight and highly efficient, enabling RFM pretraining loss to scale with a power-law dependence on both the number of databases and total token count. Experimental results demonstrate that models pretrained on this synthetic data exhibit significantly improved generalization on real-world databases, establishing PluRel as a scalable and effective training paradigm for RFMs.

0 citationsRead paper

Recent publications

Latest Papers

Bridging the Semantic-Collaborative Gap: An Asymmetric Graph Architecture for Cold-Start Item Recommendation

Jun 04, 2026

This work addresses the cold-start problem for both new content and new devices in recommender systems by formulating it as an inductive graph completion task on a temporal bipartite device–content graph. The authors propose an asymmetric graph architecture: the device tower captures collaborative signals through message passing over viewing histories, while the content tower generates embeddings solely from intrinsic semantic features, without relying on item IDs or interaction data. A Shallow-RHS design maps content semantics into a collaborative-aware embedding space. The approach is further extended to device cold-start by leveraging demographic features to construct cohort embeddings for implicit graph completion. Integrated with approximate nearest neighbor retrieval, the system enables real-time embedding generation and candidate recall. Large-scale online experiments demonstrate significant improvements in user engagement, content exposure, ramp-up speed for new content, and key metrics for new devices.

0 citationsRead paper

Revealing Interpretable Failure Modes of VLMs

May 12, 2026

This work addresses the critical yet underexplored problem of hidden, high-risk failures in vision-language models (VLMs) within safety-critical scenarios, where systematic and interpretable failure identification methods are lacking. The authors propose REVELIO, a novel framework that, for the first time, models VLM failures as interpretable combinations of semantic concepts—such as pedestrian distance or adverse weather conditions—and introduces a diversity-aware beam search coupled with Gaussian process Thompson sampling to efficiently navigate the exponentially large combinatorial space. Evaluated in autonomous driving and indoor robotics simulation environments, REVELIO uncovers previously unreported structural vulnerabilities, including spatial mislocalization, obstacle neglect, and erroneous safety hazard alerts, thereby providing actionable insights for enhancing VLM reliability and safety.

0 citationsRead paper

RelBench v2: A Large-Scale Benchmark and Repository for Relational Data

Feb 13, 2026

Relational deep learning (RDL) has emerged as a powerful paradigm for learning directly on relational databases by modeling entities and their relationships across multiple interconnected tables. As this paradigm evolves toward larger models and relational foundation models, scalable and realistic benchmarks are essential for enabling systematic evaluation and progress. In this paper, we introduce RelBench v2, a major expansion of the RelBench benchmark for RDL. RelBench v2 adds four large-scale relational datasets spanning scholarly publications, enterprise resource planning, consumer platforms, and clinical records, increasing the benchmark to 11 datasets comprising over 22 million rows across 29 tables. We further introduce autocomplete tasks, a new class of predictive objectives that require models to infer missing attribute values directly within relational tables while respecting temporal constraints, expanding beyond traditional forecasting tasks constructed via SQL queries. In addition, RelBench v2 expands beyond its native datasets by integrating external benchmarks and evaluation frameworks: we translate event streams from the Temporal Graph Benchmark into relational schemas for unified relational-temporal evaluation, interface with ReDeLEx to provide uniform access to 70+ real-world databases suitable for pretraining, and incorporate 4DBInfer datasets and tasks to broaden multi-table prediction coverage. Experimental results demonstrate that RDL models consistently outperform single-table baselines across autocomplete, forecasting, and recommendation tasks, highlighting the importance of modeling relational structure explicitly.

0 citationsRead paper

Predictive Query Language: A Domain-Specific Language for Predictive Modeling on Relational Databases

Feb 10, 2026

This work addresses the cumbersome and error-prone process of manually extracting samples and labels from relational databases for traditional machine learning modeling. To streamline this workflow, the authors propose PQL, a declarative domain-specific language inspired by SQL that enables users to define diverse predictive tasks—including regression, classification, time-series forecasting, and recommendation—through a single query directly over relational databases, with training labels automatically generated. PQL offers two implementations: one optimized for low-latency, small-scale scenarios and another designed for large-scale data processing. The approach has been validated in real-world applications such as financial fraud detection, product recommendation, and load forecasting, demonstrating its versatility, efficiency, and significant improvements in modeling productivity and scalability.

0 citationsRead paper

PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models

Feb 03, 2026

This work addresses the scarcity of publicly available multi-table relational databases for training Relational Foundation Models (RFMs) due to privacy constraints. To overcome this limitation, the authors propose PluRel, a novel framework that, for the first time, models database schemas as directed graphs and captures primary–foreign key relationships via bipartite graphs, integrating a conditional causal mechanism to generate structurally coherent and diverse synthetic multi-table data. The approach is lightweight and highly efficient, enabling RFM pretraining loss to scale with a power-law dependence on both the number of databases and total token count. Experimental results demonstrate that models pretrained on this synthetic data exhibit significantly improved generalization on real-world databases, establishing PluRel as a scalable and effective training paradigm for RFMs.

0 citationsRead paper