From the 1 of 10 linked papers with an AI index.
10 papers
Open-KNEAD: Knowledge-grounded Nutrition Estimation via Agentic Decomposition
Bruce Coburn, Jingbo Yue, Jinge Ma +3
The paper presents Open-KNEAD, a training-free, locally run agentic system that breaks down meal images into individual food items, grounds each to a nutrition database, and improv…
MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding
Siddeshwar Raghavan, Tanwi Mallick
We present MOSAIC, a multi-agent Large Language Model (LLM) framework for solving challenging scientific coding tasks. Unlike general-purpose coding, scientific workflows require a…
No Test Cases, No Problem: Distillation-Driven Code Generation for Scientific Workflows
Siddeshwar Raghavan, Tanwi Mallick
Existing multi-agent Large Language Model (LLM) frameworks for code generation typically use execution feedback and improve iteratively using Input/Output (I/O) test cases. However…
Not Your Stereo-Typical Estimator: Combining Vision and Language for Volume Perception
Gautham Vinod, Bruce Coburn, Siddeshwar Raghavan +1
Accurate volume estimation of objects from visual data is a long-standing challenge in computer vision with significant applications in robotics, logistics, and smart health. Exist…
DietDelta: A Vision-Language Approach for Dietary Assessment via Before-and-After Images
Gautham Vinod, Siddeshwar Raghavan, Bruce Coburn +1
Accurate dietary assessment is critical for precision nutrition, yet most image-based methods rely on a single pre-consumption image and provide only coarse, meal-level estimates.…
Can You Hear, Localize, and Segment Continually? An Exemplar-Free Continual Learning Benchmark for Audio-Visual Segmentation
Siddeshwar Raghavan, Gautham Vinod, Bruce Coburn +1
Audio-Visual Segmentation (AVS) aims to produce pixel-level masks of sound producing objects in videos, by jointly learning from audio and visual signals. However, real-world envir…