3 papers
cs.CV2026
Seeing Through the Weights: Privacy Leakage in Scene Coordinate Regression
Oleksii Nasypanyi, Jaemin Cho, Utku Ozbulak +2
Scene Coordinate Regression (SCR) methods are increasingly adopted for visual localization. In these approaches, the scene is implicitly encoded within a neural network that regres…
cs.CL2024
On Initializing Transformers with Pre-trained Embeddings
Ha Young Kim, Niranjan Balasubramanian, Byungkon Kang
It has become common practice now to use random initialization schemes, rather than the pre-trained embeddings, when training transformer based models from scratch. Indeed, we find…
cs.LG2023
Revisiting 16-bit Neural Network Training: A Practical Approach for Resource-Limited Learning
Juyoung Yun, Sol Choi, Francois Rameau +2
With the increasing complexity of machine learning models, managing computational resources like memory and processing power has become a critical concern. Mixed precision techniqu…