2 citations · 3 across the 5 of their papers we have counts for
4 papers · 1 filter
Beyond Accuracy: What Language-Subspace Interventions Capture, Remove, and Improve
Shaanil Punglia, Dadhichi Telwadkar, Vaibhav Rathore +2
Language-subspace interventions aim to improve multilingual reasoning by suppressing language-related components in mid-layer activations. Using MATH and MGSM across four open-weig…
Scalaris: A Scalable Enterprise Memory Architecture for Conversational AI Assistants
Devarsh Gandhi, Sarthak Pawar, Hemprasad Badgujar +3
Enterprise conversational systems require memory to personalize interactions, retain information across sessions, and maintain conversational coherence. At enterprise scale, howeve…
SuTRA : Structurally-Unified Tokenization with Root Awareness
Vaibhav Rathore, Siddhant Gole, Dadhichi Telwadkar +4
Existing subword tokenizers optimize statistical compression but ignore morphological structure, particularly the relationship between roots and affixes. This is harmful for morpho…
: Multi-modal Multi-span Medical Question Answering
Anisha Saha, Vaibhav Rathore, Abhisek Tiwari +3
The growing adoption of AI in healthcare, particularly in preventive care, highlights the critical need for accessibility and precision in Medical Question Answering (MedQA). In re…