Meow-Omni 1: A Multimodal Large Language Model for Feline Ethology

TL;DR

Meow-Omni 1 is a novel open-source multimodal language model designed for feline ethology, integrating video, audio, and physiological data for improved intent recognition in cats.

Contribution

It introduces the first quad-modal model tailored for animal behavior analysis, combining specialized scientific encoders with a unified architecture for latent-state reasoning.

Findings

Achieves 71.16% accuracy on MeowBench, surpassing existing models.

Successfully fuses multiple biological data streams for intent inference.

Provides open-source tools and datasets for further research in animal ethology.

Abstract

Deciphering animal intent is a fundamental challenge in computational ethology, largely because of semantic aliasing, the phenomenon where identical external signals (e.g., a cat's purr) correspond to radically different internal states depending on physiological context. Existing Multimodal Large Language Models (MLLMs) are blind to high-frequency biological time-series data, restricting them to superficial behavioural pattern matching rather than genuine latent-state reasoning. To bridge this gap, we introduce Meow-Omni 1, the first open-source, quad-modal MLLM purpose-built for computational ethology. It natively fuses video, audio, and physiological time-series streams with textual reasoning. Through targeted architectural adaptation, we integrate specialized scientific encoders into a unified backbone and formalize intent inference via physiologically grounded cross-modal alignment. Evaluated on MeowBench, a novel, expert-verified quad-modal benchmark, Meow-Omni 1 achieves state-of-the-art intent-recognition accuracy (71.16%), substantially outperforming leading vision-language and omni-modal baselines. We release the complete open-source pipeline including model weights, training framework, and the Meow-10K dataset, to establish a scalable paradigm for inter-species intent understanding and to advance foundation models toward real-world veterinary diagnostics and wildlife conservation.