KGLiDS was adopted by Google and Kaggle teams for production data science workflows. Its follow-on system, RAGvis, is released inside Google’s own GitHub organization (google/ragvis) and was published at EMNLP 2025.
Agentic AI systems and benchmarks (2025 to 2027)
- SIGMOD 2027 MAFBench. Unified evaluation suite for multi-agent LLM frameworks, with an architectural taxonomy over five dimensions and a controlled study of nine frameworks. Yields six evidence-based design principles. PaperCode
- Vision paper, 2026 MemState. Prototype of Governed Evolving Memory on a property-graph backend, with topic-based storage, typed dependencies and declarative policies. PaperCode
- SIGMOD 2026 Chatty-KG. Multi-agent system for on-demand conversational question answering over large knowledge graphs. Doubles accuracy (39 to 80 F1) with the same LLM under a better architecture. PaperCode
- VLDB 2026 ReSequel. LLM-assisted SQL rewriting over PostgreSQL, MySQL and DuckDB: templatizes workloads, infers rules from the catalog, verifies candidates on downsampled data. Up to 16× over native engines and 22× over LLM baselines across eight benchmarks. PaperCode
- CCS 2025 OCR-APT. Reconstructs advanced persistent threat stories from audit logs using subgraph anomaly detection and LLMs, with hard-gating assertion validation. PaperCode
- EMNLP 2025 (main) RAGvis. Knowledge-grounded RAG for exploratory data analysis and visualization; a reliable, cost-effective alternative to large-model EDA.Released in Google's own GitHub organization. PaperCode
- VLDB 2025 CatDB. Data-catalog-guided, LLM-based generator of data-centric ML pipelines, with iterative self-correction validated on the actual data. PaperCode
- SIGMOD 2025 Chatty-Gen. Dialogue benchmark generation from knowledge graphs with retrieval-augmented LLMs, cutting cost from thousands of dollars to under one dollar. PaperCode
Foundational systems
- ICDE 2024 KGLiDS. Platform for semantic abstraction, linking and automation of data science over knowledge graphs. Underlies CatDB and RAGvis.Adopted by Google and Kaggle teams for production data science workflows. PaperCode
- ICDE 2024, ICDE 2026 KGNet. GNN-enabled knowledge graph engine with task-oriented training and LLM-guided query-aware inference (KG-WISE). PaperCode
- SIGMOD 2023 KGQAn. Universal question answering over knowledge graphs, and GNN-based scalable AutoML with IBM Research. PaperCode
- VLDB 2022 KGpip. Scalable AutoML approach based on graph neural networks, developed with IBM Research. PaperCode
I also contribute to aurum-datadiscovery (MIT DBG), and to E-Store (VLDB 2015) and Solid (WWW 2016, with Tim Berners-Lee).
Earlier research projects
These projects from before the current program keep their original pages:
- The Data Civilizer System: end-to-end data discovery, integration and cleaning in large enterprises.
- Managing Linked Data at Scale (Lusail): querying, integrating and sharing geo-distributed RDF graphs.
- Elastic in-memory OLTP (E-Store)
- Large-scale analytics on strings