5 citations · 12 across the 18 of their papers we have counts for
19 papers
A Counterexample To The TF-cone Conjecture
Jindong Yan, Shenglin Zhu
The TF-cone conjecture of Asai and Iyama predicts that the TF equivalence class of an integral -vector is the open cone generated by the canonical summands of all its positive m…
Benchmarking LLM Judges for Voice-Agent Evaluation: Reliability, Calibration, and Human Oversight
Anupam Purwar, Shashank Singh, Kritika Srivastava
Evaluating conversational voice agents at scale re- quires reliable assessment methods that capture both observ- able interaction quality and the contextual judgment typically prov…
MM-tau-p: Persona-Adaptive Prompting for Robust Multi-Modal Agent Evaluation in Dual-Control Settings
Anupam Purwar, Aditya Choudhary
Current evaluation frameworks and benchmarks for LLM powered agents focus on text chat driven agents, these frameworks do not expose the persona of user to the agent, thus operatin…
When Fine-Tuning Fails and when it Generalises: Role of Data Diversity and Mixed Training in LLM-based TTS
Anupam Purwar, Aditya Choudhary
Large language models are increasingly adopted as semantic backbones for neural text-to-speech systems. However, frozen LLM representations are insufficient for modeling speaker sp…
FOCAL: A Novel Benchmarking Technique for Multi-modal Agents
Anupam Purwar, Aditya Choudhary
With the recent advancements in reasoning capabilities, tool calling using MCP servers and Audio Language Models (ALMs), development and integration of multi-modal agents (with voi…
i-LAVA: Insights on Low Latency Voice-2-Voice Architecture for Agents
Anupam Purwar, Aditya Choudhary
We experiment with a low-latency, end-to-end voice-to-voice communication model to optimize it for real-time conversational applications. By analyzing components essential to voice…
M-PACE: Mother Child Framework for Multimodal Compliance
Shreyash Verma, Amit Kesari, Vinayak Trivedi +2
Ensuring that multi-modal content adheres to brand, legal, or platform-specific compliance standards is an increasingly complex challenge across domains. Traditional compliance fra…
G-CSEA: A Graph-Based Conflict Set Extraction Algorithm for Identifying Infeasibility in Pseudo-Boolean Models
Kanishk Garg, Saranya D., Sanal Kumar +2
Workforce scheduling involves a variety of rule-based constraints-such as shift limits, staffing policies, working hour restrictions, and many similar scheduling rules-which can in…
VLMs-in-the-Wild: Bridging the Gap Between Academic Benchmarks and Enterprise Reality
Srihari Bandraupalli, Anupam Purwar
Open-source Vision-Language Models show immense promise for enterprise applications, yet a critical disconnect exists between academic evaluation and enterprise deployment requirem…
E-ARMOR: Edge case Assessment and Review of Multilingual Optical Character Recognition
Aryan Gupta, Anupam Purwar
Optical Character Recognition (OCR) in multilingual, noisy, and diverse real-world images remains a significant challenge for optical character recognition systems. With the rise o…
Prescriptive Agents based on RAG for Automated Maintenance (PARAM)
Chitranshu Harbola, Anupam Purwar
Industrial machinery maintenance requires timely intervention to prevent catastrophic failures and optimize operational efficiency. This paper presents an integrated Large Language…
KnowsLM: A framework for evaluation of small language models for knowledge augmentation and humanised conversations
Chitranshu Harbola, Anupam Purwar
In the evolving landscape of conversational AI, generating concise, context-aware, and human-like dialogue using small and medium-sized language models (LLMs) remains a complex cha…
Introducing a new hyper-parameter for RAG: Context Window Utilization
Kush Juvekar, Anupam Purwar
This paper introduces a new hyper-parameter for Retrieval-Augmented Generation (RAG) systems called Context Window Utilization. RAG systems enhance generative models by incorporati…
CultureVo: The Serious Game of Utilizing Gen AI for Enhancing Cultural Intelligence
Ajita Agarwala, Anupam Purwar, Viswanadhasai Rao
CultureVo, Inc. has developed the Integrated Culture Learning Suite (ICLS) to deliver foundational knowledge of world cultures through a combination of interactive lessons and gami…
Context-augmented Retrieval: A Novel Framework for Fast Information Retrieval based Response Generation using Large Language Model
Sai Ganesh, Anupam Purwar, Gautam B
Generating high-quality answers consistently by providing contextual information embedded in the prompt passed to the Large Language Model (LLM) is dependent on the quality of info…
VidyaRANG: Conversational Learning Based Platform powered by Large Language Model
Chitranshu Harbola, Anupam Purwar
Providing authoritative information tailored to a student's specific doubt is a hurdle in this era where search engines return an overwhelming number of article links. Large Langua…
Evaluating the Efficacy of Open-Source LLMs in Enterprise-Specific RAG Systems: A Comparative Study of Performance and Scalability
Gautam B, Anupam Purwar
This paper presents an analysis of open-source large language models (LLMs) and their application in Retrieval-Augmented Generation (RAG) tasks, specific for enterprise-specific da…
COS-Mix: Cosine Similarity and Distance Fusion for Improved Information Retrieval
Kush Juvekar, Anupam Purwar
This study proposes a novel hybrid retrieval strategy for Retrieval-Augmented Generation (RAG) that integrates cosine similarity and cosine distance measures to improve retrieval p…
Keyword Augmented Retrieval: Novel framework for Information Retrieval integrated with speech interface
Anupam Purwar, Rahul Sundar
Retrieving answers in a quick and low cost manner without hallucinations from a combination of structured and unstructured data using Language models is a major hurdle. This is wha…