3 citations · 6 across the 11 of their papers we have counts for
13 papers
SLEM: Spectrum-Aware Latent Expert Merging
Dohyeon Kim, Bedionita Soro, Bruno Andreis +1
Mixture-of-Experts (MoE) models scale model capacity efficiently by activating only a small subset of experts for each input, while still requiring all parameters to be stored in m…
MotionJEPA: Preventing Temporal Feature Collapse by Capturing Visual Changes in Latent Space
Markus Karmann, Shile Li, Christian Internò +10
Joint Embedding Predictive Architectures (JEPAs) are a promising paradigm for learning task-agnostic latent world models without visual reconstruction. However, standard JEPA train…
Procedural Pretraining for Molecular Property Prediction
Moritz Friedemann, Zachary Shinnick, Philip Torr +1
Molecular property prediction is often limited by the small size of labeled downstream datasets, motivating pretraining on large corpora of unlabeled molecules. In this work, we as…
Online Surrogate Repair: Decoupling High-Fidelity Feedback from Search Length in Closed-Loop Discovery
Xiaotang Feng, Philip Torr, Bruno Andreis
Closed-loop AI scientists can generate candidate designs at low marginal computational cost, whereas reliable feedback may require wet-lab synthesis, characterization, or high-fide…
Robust Molecular Property Prediction via Densifying Scarce Labeled Data
Jina Kim, Jeffrey Willette, Bruno Andreis +1
A widely recognized limitation of molecular prediction models is their reliance on structures observed in the training data, resulting in poor generalization to out-of-distribution…
Instruction-Guided Autoregressive Neural Network Parameter Generation
Soro Bedionita, Bruno Andreis, Song Chong +1
Learning to generate neural network parameters conditioned on task descriptions and architecture specifications is pivotal for advancing model adaptability and transfer learning. E…
Diffusion-Based Neural Network Weights Generation
Bedionita Soro, Bruno Andreis, Hayeon Lee +4
Transfer learning has gained significant attention in recent deep learning research due to its ability to accelerate convergence and enhance performance on new tasks. However, its…
Set-based Neural Network Encoding Without Weight Tying
Bruno Andreis, Soro Bedionita, Philip H. S. Torr +1
We propose a neural network weight encoding method for network property prediction that utilizes set-to-set and set-to-vector functions to efficiently encode neural network paramet…
Scalable Set Encoding with Universal Mini-Batch Consistency and Unbiased Full Set Gradient Approximation
Jeffrey Willette, Seanie Lee, Bruno Andreis +3
Recent work on mini-batch consistency (MBC) for set functions has brought attention to the need for sequentially processing and aggregating chunks of a partitioned set while guaran…
Distortion-Aware Network Pruning and Feature Reuse for Real-time Video Segmentation
Hyunsu Rhee, Dongchan Min, Sunil Hwang +2
Real-time video segmentation is a crucial task for many real-world applications such as autonomous driving and robot control. Since state-of-the-art semantic segmentation models ar…
Set-based Meta-Interpolation for Few-Task Meta-Learning
Seanie Lee, Bruno Andreis, Kenji Kawaguchi +2
Meta-learning approaches enable machine learning systems to adapt to new tasks given few examples by leveraging knowledge from related tasks. However, a large number of meta-traini…
Mini-Batch Consistent Slot Set Encoder for Scalable Set Encoding
Bruno Andreis, Jeffrey Willette, Juho Lee +1
Most existing set encoding algorithms operate under the implicit assumption that all the set elements are accessible, and that there are ample computational and memory resources to…
Set Based Stochastic Subsampling
Bruno Andreis, Seanie Lee, A. Tuan Nguyen +3
Deep models are designed to operate on huge volumes of high dimensional data such as images. In order to reduce the volume of data these models must process, we propose a set-based…