73 citations · 164 across the 12 of their papers we have counts for
13 papers
BEANS-Next and ROOTS: Broadening Audio-Language Capabilities for Bioacoustics
Christos Plachouras, David Robinson, Marius Miron +17
Bioacoustics and ethology encompass a wide range of audio understanding tasks, many of which stand to benefit from recent advances in large audio-language models. However, progress…
Beyond task performance: Decoding bioacoustic embeddings with speech features
Ines Nolasco, Jules Cauzinille, Marius Miron +8
Pretrained audio embeddings are standard in bioacoustics, yet little is known about which acoustic features these models encode, nor which are useful for a given task. This hinders…
Multi-layer attentive probing improves transfer of audio representations for bioacoustics
Marius Miron, David Robinson, Masato Hagiwara +15
Probing heads map the representations learned from audio by a machine learning model to downstream task labels and are a key component in evaluating representation learning. Most b…
Beyond the Baseband: Adaptive Multi-Band Encoding for Full-Spectrum Bioacoustics Classification
Eklavya Sarkar, Marius Miron, David Robinson +6
Animals hear and vocalize across frequency ranges that differ substantially from humans, often extending into the ultrasonic domain. Yet most computational bioacoustics systems rel…
BAGEL: Benchmarking Animal Knowledge Expertise in Language Models
Jiacheng Shen, Masato Hagiwara, Milad Alizadeh +9
Large language models have shown strong performance on broad-domain knowledge and reasoning benchmarks, but it remains unclear how well language models handle specialized animal-re…
AVEX: What Matters for Animal Vocalization Encoding
Marius Miron, David Robinson, Milad Alizadeh +14
Bioacoustics, the study of sounds produced by living organisms, plays a vital role in conservation, biodiversity monitoring, and behavioral studies. Many tasks in this field, such…
On Leakage of Code Generation Evaluation Datasets
Alexandre Matton, Tom Sherborne, Dennis Aumiller +7
In this paper, we consider contamination by code generation test sets, in particular in their use in modern large language models. We discuss three possible sources of such contami…
Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients
Milad Alizadeh, Shyam A. Tailor, Luisa M Zintgraf +4
Pruning neural networks at initialization would enable us to find sparse models that retain the accuracy of the original network while consuming fewer computational resources for t…
COIN++: Neural Compression Across Modalities
Emilien Dupont, Hrushikesh Loya, Milad Alizadeh +3
Neural compression algorithms are typically based on autoencoders that require specialized encoder and decoder architectures for different data modalities. In this paper, we propos…
COIN: COmpression with Implicit Neural representations
Emilien Dupont, Adam Goliński, Milad Alizadeh +2
We propose a new simple approach for image compression: instead of storing the RGB values for each pixel of an image, we store the weights of a neural network overfitted to the ima…
Single Shot Structured Pruning Before Training
Joost van Amersfoort, Milad Alizadeh, Sebastian Farquhar +2
We introduce a method to speed up training by 2x and inference by 3x in deep neural networks using structured pruning applied before training. Unlike previous works on pruning befo…
Gradient Regularization for Quantization Robustness
Milad Alizadeh, Arash Behboodi, Mart van Baalen +3
We analyze the effect of quantizing weights and activations of neural networks on their loss and derive a simple regularization scheme that improves robustness against post-trainin…
A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks
Angelos Filos, Sebastian Farquhar, Aidan N. Gomez +6
Evaluation of Bayesian deep learning (BDL) methods is challenging. We often seek to evaluate the methods' robustness and scalability, assessing whether new tools give `better' unce…