Genre
Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima
To address this gap, we study deterministic/stochastic versions of SAM with practical configurations (i.e., constant
Segment Anything in 3D with NeRFs
We refer to the proposed solution as SA3D, for Segment Anything in 3D. It is only required to provide a manual segmentation prompt ( e.g., rough points) for the target object in a single view, which is used to generate its 2D mask in this view with SAM.
ed519dacc89b2bead3f453b0b05a4a8b-Supplemental.pdf
Figure 11: Comparison of HCAM (labeled as HTM) with different chunk sizes to TrXL across the different ballet levels. The performance of the HCAM model is robust to varying chunk size, indicating that HCAM does not need a task-relevant segmentation to perform well.
Multi-Lingual Acquisition on Multimodal Pre-training for Cross-modal Retrieval
Vision and diverse languages are important information sources in our living world.
Regularizing Trajectory Optimization with Denoising Autoencoders
Rinu Boney, Norman Di Palo, Mathias Berglund, Alexander Ilin, Juho Kannala, Antti Rasmus, Harri Valpola
Neural Information Processing Systems http://nips.cc/
Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models Jiaqi Li
Machine unlearning (MU) empowers individuals with the'right to be forgotten' by removing their private or sensitive information encoded in machine learning models. However, it remains uncertain whether MU can be effectively applied to Multimodal Large Language Models (MLLMs), particularly in scenarios of forgetting the leaked visual data of concepts.
Extensive-Form Game Solving via Blackwell Approachability on Treeplexes
In this paper, we focus on solving Extensive-F orm Games (EFGs).
