GAMMA on GAMMA

848

Tue, 16 Jun 2026 00:00:00 +0000

849

Tue, 09 Jun 2026 00:00:00 +0000

847

Sun, 31 May 2026 12:00:00 +0000

852

Wed, 22 Apr 2026 00:00:00 +0000

GAMMA Lab & NVIDIA Release Audio Flamingo Next for Open Audio-Language Reasoning

Tue, 14 Apr 2026 00:00:00 -0400

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-Thought, a reasoning paradigm that grounds intermediate reasoning steps to timestamps in long audio. This enables more faithful and interpretable reasoning over complex audio inputs, including speech, environmental sounds, music, and long-form recordings.

The model family includes three specialized variants: AF-Next-Instruct for general audio question answering, AF-Next-Think for multi-step audio reasoning, and AF-Next-Captioner for detailed audio captioning. The system supports long audio inputs up to 30 minutes and is trained using large-scale audio data spanning more than 1 million hours.

Together, AF-Next advances open research in audio-language modeling and provides a strong foundation for multimodal systems that can understand, reason over, and interact with real-world audio.

Learn more:
https://www.marktechpost.com/2026/04/14/nvidia-and-the-university-of-maryland-researchers-released-audio-flamingo-next-af-next-a-super-powerful-and-open-large-audio-language-model/

Paper:
https://arxiv.org/abs/2604.10905

Lin and Manocha Receive 2026 IEEE ICRA Most Influential Paper Award

Fri, 10 Apr 2026 00:00:00 -0400

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 Obstacles for real-time multi-agent navigation.”

The award recognizes research that has had a lasting impact on the robotics and automation community. The honored work introduced influential methods for real-time multi-agent navigation, helping robots and virtual agents avoid collisions while moving efficiently in shared spaces.

The recipients will be honored during the IEEE International Conference on Robotics and Automation (ICRA 2026) award ceremony in May 2026.

Learn more:
https://www.ieee-ras.org/2026-ieee-ras-award-recipients-announced/

850

Sun, 29 Mar 2026 00:00:00 +0000

854

Sun, 01 Mar 2026 00:00:00 +0000

GAMMA Lab & Apple Develop AMUSE to Advance Agentic Multimodal Reasoning

Wed, 18 Feb 2026 00:00:00 -0500

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 AI systems operating in complex, real-world conversational settings.

AMUSE focuses on agentic multi-speaker reasoning — requiring models to track who is speaking over time, ground dialogue in visual context, and generate coherent multimodal summaries. The benchmark reveals significant limitations in existing multimodal large language models when reasoning across audio, vision, and language simultaneously.

Alongside the benchmark, the team introduces RAFT, a data-efficient alignment framework that combines reward optimization with intrinsic multimodal self-evaluation, substantially improving performance on agentic audio-visual tasks.

Together, AMUSE and RAFT provide a new foundation for advancing multimodal AI systems capable of sustained, structured reasoning across modalities.

Learn more:
https://machinelearning.apple.com/research/amuse

Sonal Kumar and Younghan Lee received the Outstanding Graduate Assistant Award at UMD

Tue, 03 Feb 2026 00:00:00 -0500

GAMMA presented 3 papers at AAAI 2026

Thu, 01 Jan 2026 10:49:38 -0400

GAMMA Collaborates with NVIDIA on Music Flamingo, Adopted by Universal Music Group

Thu, 01 Jan 2026 00:00:00 -0500

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 the creative and entertainment industries.

Music Flamingo highlights how advances in multimodal learning can support music analysis, content creation, and new forms of human–AI collaboration.

Coverage:
https://www.theverge.com/news/856849/universal-music-nvidia-ai-deal

851

Sun, 23 Nov 2025 00:00:00 +0000

GAMMA organized RARA: First Workshop on Grounding Documents with Reasoning, Agents, Retrieval, and Attribution at ICDM 2025

Wed, 12 Nov 2025 00:00:00 -0500

GAMMA will present 4 papers at EMNLP 2025

Mon, 06 Oct 2025 10:49:38 -0400