4 papers
WorkflowPerturb: Calibrated Stress Tests for Evaluating Multi-Agent Workflow Metrics
Madhav Kanda, Sharad Agarwal, Rodrigo Fonseca +2
Multi-agent LLM systems that generate structured workflows from natural-language requests are now deployed in production across cloud automation, DevOps, and enterprise process orc…
Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping
Dwip Dalal, Gautam Vashishtha, Utkarsh Mishra +6
Multimodal large language models (MLLMs) often miss small details and spatial relations in cluttered scenes, leading to errors in fine-grained perceptual grounding. We introduce At…
RefineStat: Efficient Exploration for Probabilistic Program Synthesis
Madhav Kanda, Shubham Ugare, Sasa Misailovic
Probabilistic programming offers a powerful framework for modeling uncertainty, yet statistical model discovery in this domain entails navigating an immense search space under stri…
SpiroActive: Active Learning for Efficient Data Acquisition for Spirometry
Ankita Kumari Jain, Nitish Sharma, Madhav Kanda +1
Respiratory illnesses are a significant global health burden. Respiratory illnesses, primarily Chronic obstructive pulmonary disease (COPD), is the seventh leading cause of poor he…