5 citations · 7 across the 7 of their papers we have counts for
7 papers
CeQe: Grounding Lexical Retrieval in Semantic Evidence
Adam Kahirov, Umesh Deshpande, Swaminathan Sundararaman
Lexical retrieval (BM25) captures exact keyword matches and weights terms by corpus-wide significance, but it is blind to the semantic vocabulary gap: when a relevant document phra…
Hierarchical BM25: Lexical Search at Billion-Document Scale
Umesh Deshpande, Swaminathan Sundararaman
A flat BM25 index over one billion documents occupies about 400 GB. Holding it in memory requires DRAM proportional to corpus size. Serving it from disk takes 4-12 seconds per quer…
Symbiosis: Multi-Adapter Inference and Fine-Tuning
Saransh Gupta, Umesh Deshpande, Travis Janssen +1
Parameter-efficient fine-tuning (PEFT) allows model builders to capture the task-specific parameters into adapters, which are a fraction of the size of the original base model. Pop…
ZipNN: Lossless Compression for AI Models
Moshik Hershcovitch, Andrew Wood, Leshem Choshen +7
With the growth of model sizes and the scale of their deployment, their sheer size burdens the infrastructure requiring more network and more storage to accommodate these. While th…
Lossless and Near-Lossless Compression for Foundation Models
Moshik Hershcovitch, Leshem Choshen, Andrew Wood +4
With the growth of model sizes and scale of their deployment, their sheer size burdens the infrastructure requiring more network and more storage to accommodate these. While there…
MPP: Model Performance Predictor
Sindhu Ghanta, Sriram Subramanian, Lior Khermosh +5
Operations is a key challenge in the domain of machine learning pipeline deployments involving monitoring and management of real-time prediction quality. Typically, metrics like ac…
ML Health: Fitness Tracking for Production Models
Sindhu Ghanta, Sriram Subramanian, Lior Khermosh +5
Deployment of machine learning (ML) algorithms in production for extended periods of time has uncovered new challenges such as monitoring and management of real-time prediction qua…