GAMMA Lab researchers collaborated with NVIDIA to release Audio Flamingo Next (AF-Next), a next-generation open audio-language model designed for advanced reasoning over speech, sound, and music. AF-Next introduces Temporal Audio Chain-of-T…
University of Maryland professors Ming Lin and Dinesh Manocha, together with Jur van den Berg, received the 2026 IEEE International Conference on Robotics and Automation Most Influential Paper Award for their work on “Reciprocal Velocity Ob…
GAMMA Lab researchers collaborated with Apple Machine Learning Research to develop AMUSE (Audio-Visual Benchmark and Alignment framework for Agentic Multi-Speaker Understanding), a new benchmark designed to evaluate and improve multimodal A…
GAMMA members collaborated with NVIDIA to develop Music Flamingo, a multimodal AI system for music understanding and generation. The technology is being adopted by Universal Music Group, demonstrating the growing role of multimodal AI in th…
PDF Project Google Scholar Texture Massive Models PDF Google Scholar Ray Tracing Massive Models PDF Project Video Google Scholar Ray Tracing GPGPU Shadow Rendering Massive Models PDF Project Video Google Scholar Shadow Rendering Hidden Surf…
GAMMA’s research includes design and implementation of algebraic, geometric, and scientific algorithms and their applications to computer graphics, robotics, virtual environments, CAD/CAM, acoustics, pedestrian dynamics, and medical simulat…
AI-driven virtual conversational assistant. Dost's gestures, facial expressions, and speech are generated in real-time using state-of-the-art research in affective computing, emotional modeling, character and speech generation, and virtual
Download the pre-trained models for 2D object detection and action-behavior prediction from the GitHub link above. State-of-the-art 2D object detection, which succeeds on existing datasets like Waymo, nuScenes, and Apolloscape, fails on our…
Please cite our work if you found it useful, This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. The labels corresponding to each video inside the folder videos_original is stored i…
TRAF Dataset: We provide a dataset of dense and heterogeneous traffic videos. The dataset consists of the following road-agent categories – car, bus, truck, rickshaw, pedestrian, scooter, motorcycle, and other roadagents such as carts and a…
We present novel algorithms for identifying emotion, dominance, and friendliness characteristics of pedestrians, as well detecting deceptive traits in walking, based on their motion behaviors. We also propose models for conveying emotions,
The dataset can be found here. Please cite this paper if you found the dataset useful: We show example videos. Can you spot the cows !?: Rohan Chandra, Uttaran Bhattacharya, Aniket Bera, and Dinesh Manocha, TraPHic: Trajectory Prediction in…