4 papers
From Numbers to Judgment: Specialist LLM Agents and Reinforcement Learning for European Listed Real Estate
Pardis Taghavi, Santosh Bhavani
We study whether the localized numerical operations and integrative judgments of financial analysis benefit from the same form of LLM specialization. Larix maps a 16-lens European…
Spec Kit Agents: Context-Grounded Agentic Workflows
Pardis Taghavi, Santosh Bhavani
Spec-driven development (SDD) with AI coding agents provides a structured workflow, but agents often remain "context blind" in large, evolving repositories, leading to hallucinated…
Scalable Training of Mixture-of-Experts Models with Megatron Core
Zijie Yan, Hongxiao Bai, Xin Yao +42
Scaling Mixture-of-Experts (MoE) training introduces systems challenges absent in dense models. Because each token activates only a subset of experts, this sparsity allows total pa…
Interest Maximization in Social Networks
Rahul Kumar Gautam, Anjeneya Swami Kare, S. Durga Bhavani
Nowadays, organizations use viral marketing strategies to promote their products through social networks. It is expensive to directly send the product promotional information to al…