2.3k citations · 2.4k across the 17 of their papers we have counts for
17 papers
OpenJarvis: Personal AI, On Personal Devices
Jon Saad-Falcon, Avanika Narayan, Robby Manihani +10
Personal AI stacks, like OpenClaw and Hermes Agent, are becoming central to daily work, yet they route nearly every query (often over sensitive local data) to cloud-hosted frontier…
An Information Theoretic Perspective on Agentic System Design
Shizhe He, Avanika Narayan, Ishan S. Khare +3
Agentic language model (LM) systems power modern applications like "Deep Research" and "Claude Code," and leverage multi-LM architectures to overcome context limitations. Beneath t…
Intelligence per Watt: Measuring Intelligence Efficiency of Local AI
Jon Saad-Falcon, Avanika Narayan, Hakki Orhun Akengin +12
Large language model (LLM) queries are predominantly processed by frontier models in centralized cloud infrastructure. Demand growth strains this paradigm faster than providers can…
Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models
Avanika Narayan, Dan Biderman, Sabri Eyuboglu +4
We investigate an emerging setup in which a small, on-device language model (LM) with access to local data communicates with a frontier, cloud-hosted LM to solve real-world tasks i…
Cookbook: A framework for improving LLM generative abilities via programmatic data generating templates
Avanika Narayan, Mayee F. Chen, Kush Bhatia +1
Fine-tuning large language models (LLMs) on instruction datasets is a common way to improve their generative capabilities. However, instruction datasets can be expensive and time-c…
WONDERBREAD: A Benchmark for Evaluating Multimodal Foundation Models on Business Process Management Tasks
Michael Wornow, Avanika Narayan, Ben Viggiano +15
Existing ML benchmarks lack the depth and diversity of annotations needed for evaluating models on business process management (BPM) tasks. BPM is the practice of documenting, meas…