Contrastive Sparse Representation learning approach for ultra-sparse embeddings that achieves 7x speedup over Matryoshka Representation Learning with 300x improvements in compute and memory efficiency.

Representation learning approach encoding information at multiple granularities, allowing embeddings to be truncated while maintaining performance. Enables 14x smaller sizes and 5x faster search.

REAPER (Reasoning based Retrieval Planning for Complex RAG Systems) is a research framework that addresses multi-step retrieval planning in complex Retrieval-Augmented Generation scenarios. It enables retrieval systems to plan and execute reasoning-aware retrieval strategies rather than relying on simple similarity-based matching.

SC'25 Workshop paper characterizing Qdrant vector database performance on high-performance computing platforms, bridging AI and HPC workloads.

Research paper proposing a decoupled storage architecture for vector databases that improves update speed by 10.05x for insertions and 6.89x for deletions through innovative design.

Research on using Monte Carlo Tree Search algorithms for optimizing vector index construction and search strategies. Explores adaptive decision-making during graph building and query routing.