# Ecologically-Constrained Task Arithmetic for Multi-Taxa Bioacoustic Classifiers Without Shared Data

arXiv: https://arxiv.org/abs/2605.03914 · HTML: https://mlsanity.com/paper/2605.03914/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 5 May 2026.

## Builds on (most cited first, 15 of 15)

- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [Linear Mode Connectivity and the Lottery Ticket Hypothesis](https://mlsanity.com/paper/1912.05671/) (2019)
- [BEATs: Audio Pre-Training with Acoustic Tokenizers](https://mlsanity.com/paper/2212.09058/) (2022)
- [DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling](https://mlsanity.com/paper/2406.11617/) (2024)
- [Computational bioacoustics with deep learning: a review and roadmap](https://mlsanity.com/paper/2112.06725/) (2021)
- [BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics](https://mlsanity.com/paper/2403.10380/) (2024)
- [Perch 2.0: The Bittern Lesson for Bioacoustics](https://mlsanity.com/paper/2508.04665/) (2025)
- [Task Arithmetic Through The Lens Of One-Shot Federated Learning](https://mlsanity.com/paper/2411.18607/) (2024)
- [AnuraSet: A dataset for benchmarking Neotropical anuran calls identification in passive acoustic monitoring](https://mlsanity.com/paper/2307.06860/) (2023)
- [The Search for Squawk: Agile Modeling in Bioacoustics](https://mlsanity.com/paper/2505.03071/) (2025)
- [Distilling a speech and music encoder with task arithmetic](https://mlsanity.com/paper/2505.13270/) (2025)
- [Model Merging Improves Zero-Shot Generalization in Bioacoustic Foundation Models](https://mlsanity.com/paper/2511.05171/) (2025)
- [Weakly Supervised Detection and Temporal Localization of Whale Calls in Long-Duration Bioacoustic Data](https://mlsanity.com/paper/2502.20838/) (2025)

## Abstract (arXiv)

Training data for bioacoustics is scattered across taxa, regions, and institutions. Centralizing it all is often infeasible. We show that independently fine-tuned BEATs encoders can be composed into a unified 661-species classifier via task vector arithmetic without sharing data. We find that bioacoustic task vectors are near-orthogonal (cosine 0.01-0.09). Their separation aligns closely with spectral distribution distance, a gradient consistent with the acoustic niche hypothesis. This geometry makes simple averaging optimal while sign-conflict methods reduce accuracy by one to six percentage points. Composition also creates an asymmetric gap: species-rich groups lose accuracy relative to joint training while underrepresented taxa gain, a redistribution useful for equitable biodiversity monitoring. We verify linear mode connectivity across all taxonomic pairs, demonstrate zero-shot transfer to new regions, and identify domain negation as a boundary condition where composition fails. These results enable a collaborative paradigm for bioacoustics where institutions share only task vectors to assemble multi-taxa classifiers, preserving data privacy.