Get started
Author

Srinivasan Manoharan

Observed name: Manoharan, Srinivasan
Observed institution: PayPal (United States)
OpenAlex ID: A5138069125
Our Own Jev: Typed Decisions in One Forward Pass, from an In-House Judge to Open LoRA Models
2026 · Weng, Yuchuan, Liu, Chi, et al. · arXiv (Cornell University) · 2
PDF
Semantic Tool Discovery for Large Language Models: A Vector-Based Approach to MCP Tool Selection
2026 · Mudunuri, Sarat, Wan, Jian, et al. · arXiv (Cornell University) · 2
PDF
Zero-Trust Authorization and Discovery for Enterprise MCP
2026 · Li, Huan, Wang, Yuwei, et al. · arXiv (Cornell University) · 1
PDF
Hybrid Semantic Tool Discovery for Enterprise MCP Gateway: Architecture and Implementation
2026 · Saha, Olympia, Wang, Amy, et al. · arXiv (Cornell University) · 1
PDF
A Gateway Architecture for Enterprise MCP Authentication: Unifying Heterogeneous Auth, Identity Delegation, and the User / Non-User Persona Problem
2026 · Kumar, Suraj, Wang, Amy, et al. · arXiv (Cornell University) · 1
PDF
Governing Enterprise AI Traffic at Scale: Design and Operation of a Policy-Driven, Multi-Vendor LLM Gateway on Envoy
2026 · Sasidharan, Mithun, Manoharan, Srinivasan, et al. · arXiv (Cornell University)
PDF
Student-Guided Teacher Distillation for Efficient LLM Task Routing: Positioning Against Jev-Style System-1 Classifiers
2026 · Wu, Haifeng, Manoharan, Srinivasan, et al. · arXiv (Cornell University)
PDF
Task-to-Model Optimization for Enterprise LLM Coding Assistants: A Data-Driven Framework for Cost-Optimal Routing
2026 · Manoharan, Srinivasan, Zhao, Junhua, et al. · arXiv (Cornell University)
PDF
Accelerating Paypal's Commerce Agent with Speculative Decoding: An Empirical Study on EAGLE3 with Fine-Tuned Nemotron Models
2026 · Ally Qin, Jian Wan, et al. · IEEE International Conference on Big Data Computing Service and Applications (BigDataService)
PDF
RLM-Cascade: Response-Level Speculative Decoding for Cost-Efficient LLM API Serving
2026 · Wu, Haifeng, Manoharan, Srinivasan, et al. · arXiv (Cornell University)
PDF
Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data
2026 · Manoharan, Srinivasan, Nallusamy, Dilipkumar, et al. · arXiv (Cornell University)
PDF
Beyond Output Matching: Preserving Internal Geometry in NVFP4 LLM Distillation
2026 · Tu, Fangbo, Zhao, Junhua, et al. · arXiv (Cornell University)
PDF
Self-Distillation as a Performance Recovery Mechanism for LLMs: Counteracting Compression and Catastrophic Forgetting
2026 · Liu, Chi, Chen, Xin, et al. · arXiv (Cornell University)
PDF
NEMO-4-PAYPAL: Leveraging NVIDIA's Nemo Framework for empowering PayPal's Commerce Agent
2025 · Garg, Sudhanshu, Wang, Andrew, et al. · arXiv (Cornell University)
PDF
Works count: 14
Citation count: 7
H-index: 2
I10-index:
Year
Topic
Type