Europe
Efficient Model-Free Exploration in Low-Rank MDPs
What are the right computational primitives for exploration?
DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization
Diffusion models have achieved remarkable progress in the field of image generation due to their outstanding capabilities.
Neural Template Regularization-Supplementary Material-Aditya V ora
Below are the details of each step. This allows us to input any number of images as input. This split is the same split that is used by [8]. This includes many scenes with complex architecture and backgrounds. We show additional results on the BlendedMVS dataset for 3 new objects.
DiViNeT: 3D Reconstruction from Disparate Views via Neural Template Regularization Aditya V ora
Several recent attempts have been made on neural reconstruction from sparse views.
d2b752ed4726286a4b488ae16e091d64-Supplemental-Conference.pdf
Table 3 presents comprehensive details of the TrojAI dataset. PICCOLO is a backdoor scanning tool aiming at detecting whether a language model is backdoored. It cannot reverse engineer exact triggers but optimizes a list of surrogate triggers that can induce ASR. The surrogate triggers by PICCOLO cannot be directly used. Table 4 documents the optimal prompts identified via fuzzing for each model.
Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models Guillermo Ortiz-Jimenez
We present a comprehensive study of task arithmetic in vision-language models and show that weight disentanglement is the crucial factor that makes it effective. This property arises during pre-training and manifests when distinct directions in weight space govern separate, localized regions in function space associated with the tasks.