27 citations · 33 across the 12 of their papers we have counts for
13 papers
Beyond Context Length: Characterising the Difficulty of Long-Context Reasoning
Shiwen Qin, Cameron Barker, Henry Gouk +4
Long-context language models support ever longer context windows, and evaluations typically treat context length as the main indicator of difficulty. However, context length alone…
COP-GEN: Latent Diffusion Transformer for Copernicus Earth Observation Data
Miguel Espinosa, Eva Gmelich Meijling, Valerio Marsocci +2
Earth observation applications increasingly rely on data from multiple sensors, including optical, radar, elevation, and land-cover. Relationships between modalities are fundamenta…
Evolutionary Architecture Search through Grammar-Based Sequence Alignment
Adri Gómez Martín, Felix Möller, Steven McDonagh +5
Neural architecture search (NAS) in expressive search spaces is a computationally hard problem, but it also holds the potential to automatically discover completely novel and perfo…
ONNX-Net: Towards Universal Representations and Instant Performance Prediction for Neural Architectures
Shiwen Qin, Alexander Auras, Shay B. Cohen +4
Neural architecture search (NAS) automates the design process of high-performing architectures, but remains bottlenecked by expensive performance evaluation. Most existing studies…
No time to train! Training-Free Reference-Based Instance Segmentation
Miguel Espinosa, Chenhongyi Yang, Linus Ericsson +2
The performance of image segmentation models has historically been constrained by the high cost of collecting large-scale annotated data. The Segment Anything Model (SAM) alleviate…
COP-GEN-Beta: Unified Generative Modelling of COPernicus Imagery Thumbnails
Miguel Espinosa, Valerio Marsocci, Yuru Jia +2
In remote sensing, multi-modal data from various sensors capturing the same scene offers rich opportunities, but learning a unified representation across these modalities remains a…
Transferrable Surrogates in Expressive Neural Architecture Search Spaces
Shiwen Qin, Gabriela Kadlecová, Martin Pilát +5
Neural architecture search (NAS) faces a challenge in balancing the exploration of expressive, broad search spaces that enable architectural innovation with the need for efficient…
There is no SAMantics! Exploring SAM as a Backbone for Visual Understanding Tasks
Miguel Espinosa, Chenhongyi Yang, Linus Ericsson +2
The Segment Anything Model (SAM) was originally designed for label-agnostic mask generation. Does this model also possess inherent semantic understanding, of value to broader visua…
einspace: Searching for Neural Architectures from Fundamental Operations
Linus Ericsson, Miguel Espinosa, Chenhongyi Yang +5
Neural architecture search (NAS) finds high performing networks for a given task. Yet the results of NAS are fairly prosaic; they did not e.g. create a shift from convolutional str…
Hyperparameter Selection in Continual Learning
Thomas L. Lee, Sigrid Passano Hellan, Linus Ericsson +2
In continual learning (CL) -- where a learner trains on a stream of data -- standard hyperparameter optimisation (HPO) cannot be applied, as a learner does not have access to all o…
EgoPoseFormer: A Simple Baseline for Stereo Egocentric 3D Human Pose Estimation
Chenhongyi Yang, Anastasia Tkach, Shreyas Hampali +3
We present EgoPoseFormer, a simple yet effective transformer-based model for stereo egocentric human pose estimation. The main challenge in egocentric pose estimation is overcoming…
PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition
Chenhongyi Yang, Zehui Chen, Miguel Espinosa +4
We present PlainMamba: a simple non-hierarchical state space model (SSM) designed for general visual recognition. The recent Mamba model has shown how SSMs can be highly competitiv…
WidthFormer: Toward Efficient Transformer-based BEV View Transformation
Chenhongyi Yang, Tianwei Lin, Lichao Huang +1
We present WidthFormer, a novel transformer-based module to compute Bird's-Eye-View (BEV) representations from multi-view cameras for real-time autonomous-driving applications. Wid…