13 citations · 32 across the 10 of their papers we have counts for
3 papers · 1 filter
BOKBO (Best of K Bad Options): Calibrated Abstention for VLA Policies
Anya Singh, Cabrel Happi, Jai Relan +2
Test-time scaling for vision-language-action (VLA) policies, methods such as RoboMonkey, SEAL, MG-Select, and V-GPS, samples K candidate action chunks at inference and executes the…
Training Neural Networks with Fixed Sparse Masks
Yi-Lin Sung, Varun Nair, Colin Raffel
During typical gradient-based training of deep neural networks, all of the model's parameters are updated at each iteration. Recent work has shown that it is possible to update onl…
RealMix: Towards Realistic Semi-Supervised Deep Learning Algorithms
Varun Nair, Javier Fuentes Alonso, Tony Beltramelli
Semi-Supervised Learning (SSL) algorithms have shown great potential in training regimes when access to labeled data is scarce but access to unlabeled data is plentiful. However, o…