Kaousheik Jayakumar

Selected publications and preprints.

Sreyan Ghosh, Arushi Goel, Kaousheik Jayakumar, et al. (in collaboration with NVIDIA)

Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos

Preprint 路 2026 Coming Soon 馃搫 Paper
Audio-Visual Flamingo Logo
Sreyan Ghosh, Arushi Goel, Kaousheik Jayakumar, et al. (in collaboration with NVIDIA)

Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music

Preprint 路 2026 馃搫 arXiv 馃寪 Project Page 馃 HuggingFace
Audio Flamingo Next Logo
Arushi Goel, Sreyan Ghosh, Vatsal Agarwal, Nishit Anand, Kaousheik Jayakumar, et al. (in collaboration with NVIDIA)

MMOU - Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos

Preprint 路 2026 馃搫 arXiv 馃寪 Project Page 馃 HuggingFace
MMOU Logo
Ramaneswaran Selvakumar*, Kaousheik Jayakumar* et al.

Do Audio-Visual Large Language Models Really See and Hear?

CVPR Findings 路 2026 馃搫 arXiv 馃寪 Project Page
CVPR Paper Logo
Mahesh Ramesh, Kaousheik Jayakumar, et al.

Sparks of Cooperative Reasoning: Multi-turn LLM Analysis through Hanabi

Preprint 路 2026 馃搫 arXiv 馃寪 Project Page
Hanabi Logo
Kaousheik Jayakumar, et al.

Multilingual ASR Systems for Indian Languages

Interspeech 路 2023 馃搫 arXiv
Tag Team Logo