6 papers
Models for minimalist RAG: B1ade 335M Embedding and 1B Parameter Small Language Models
Shreyas Subramanian, Mecit Gungor, Vikram Elango
Language and embedding models used in RAG systems are conventionally assumed to require large-scale pretraining and explicit grounding supervision. We present B1ade, an efficient R…
Super Weights in LLMs and the Failure of Selective Training
Shreyas Subramanian, Adewale Akinfaderin, Akarsha Sehwag
Recent work identified Super Weights, individual parameters whose removal degrades model performance by orders of magnitude. We show that this degradation due to pruning Super Weig…
Keyword search is all you need: Achieving RAG-Level Performance without vector databases using agentic tool use
Shreyas Subramanian, Adewale Akinfaderin, Yanyan Zhang +4
While Retrieval-Augmented Generation (RAG) has proven effective for generating accurate, context-based responses based on existing knowledge bases, it presents several challenges i…
VERAFI: Verified Agentic Financial Intelligence through Neurosymbolic Policy Generation
Adewale Akinfaderin, Shreyas Subramanian
Financial AI systems suffer from a critical blind spot: while Retrieval-Augmented Generation (RAG) excels at finding relevant documents, language models still generate calculation…
Small Language Models for Efficient Agentic Tool Calling: Outperforming Large Models with Targeted Fine-tuning
Polaris Jhandi, Owais Kazi, Shreyas Subramanian +1
As organizations scale adoption of generative AI, model cost optimization and operational efficiency have emerged as critical factors determining sustainability and accessibility.…
Plan-and-Write: Structure-Guided Length Control for LLMs without Model Retraining
Adewale Akinfaderin, Shreyas Subramanian, Akarsha Sehwag
Length control in Large Language Models (LLMs) is a crucial but under-addressed challenge, with applications ranging from voice interfaces requiring concise responses to research s…