activity
20242026
collaborators

7 papers

cs.CV2026

Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding

Arsha Nagrani, Jasper Uijilings, Shyamal Buch +6

Video reasoning models are a core component of egocentric and embodied agents. However, standard benchmarks for assessing models provide only evaluation of the output (e.g. the ans…

cs.CV2026

MINERVA-Cultural: A Benchmark for Cultural and Multilingual Long Video Reasoning

Darshan Singh, Arsha Nagrani, Kawshik Manikantan +6

Recent advancements in video models have shown tremendous progress, particularly in long video understanding. However, current benchmarks predominantly feature western-centric data…

cs.CV2025

CAViAR: Critic-Augmented Video Agentic Reasoning

Sachit Menon, Ahmet Iscen, Arsha Nagrani +3

Video understanding has seen significant progress in recent years, with models' performance on perception from short clips continuing to rise. Yet, multiple recent benchmarks, such…

cs.CV2025

VideoPrism: A Foundational Visual Encoder for Video Understanding

Long Zhao, Nitesh B. Gundavarapu, Liangzhe Yuan +16

We introduce VideoPrism, a general-purpose video encoder that tackles diverse video understanding tasks with a single frozen model. We pretrain VideoPrism on a heterogeneous corpus…

cs.LG2025

MINERVA: Evaluating Complex Video Reasoning

Arsha Nagrani, Sachit Menon, Ahmet Iscen +9

Multimodal LLMs are turning their focus to video benchmarks, however most video benchmarks only provide outcome supervision, with no intermediate or interpretable reasoning steps.…

cs.LG2025

Neptune: The Long Orbit to Benchmarking Long Video Understanding

Arsha Nagrani, Mingda Zhang, Ramin Mehran +10

We introduce Neptune, a benchmark for long video understanding that requires reasoning over long time horizons and across different modalities. Many existing video datasets and mod…