Lattice AI Research

Research focus

Computer Vision (2)Multimodal Models (2)Natural Language Processing (1)Eval Frameworks & Benchmarks (1)Speech & Audio (1)

Frequent co-authors

Gautham Vinod (2)Fengqing Zhu (2)S. Raghavan (1)Siddeshwar Raghavan (1)

Papers (2)

Apr 7, 2026

Gautham Vinod +3Apr 7, 2026·also Affiliation:

DietDelta: A Vision-Language Approach for Dietary Assessment via Before-and-After Images

Ditch the depth sensors: DietDelta uses before-and-after photos and natural language to pinpoint exactly what you ate, item by item.

Gautham Vinod, S. Raghavan, Bruce Coburn +1

Computer Vision Multimodal Models Natural Language Processing

Mar 9, 2026

Mar 9, 2026·also Affiliation:

Can You Hear, Localize, and Segment Continually? An Exemplar-Free Continual Learning Benchmark for Audio-Visual Segmentation

A new benchmark reveals how existing audio-visual segmentation models crumble when faced with the dynamic, ever-changing audio and visual environments of the real world.

Siddeshwar Raghavan, Gautham Vinod, Bruce Coburn +1

Computer Vision Eval Frameworks & Benchmarks Multimodal Models+1

Search

Bruce Coburn

Research focus

Frequent co-authors

Papers (2)