Technology
SCube: Instant Large-Scale Scene Reconstruction using VoxSplats
We present SCube, a novel method for reconstructing large-scale 3D scenes (geometry, appearance, and semantics) from a sparse set of posed images.
From Trainable Negative Depth to Edge Heterophily in Graphs Y uchen Y an
Upon increasing the depth, the over-smoothing issue arises: a GCN's
Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
Our study aims to promote a higher standard of empirical rigor in the field of graph machine learning, encouraging more accurate comparisons and evaluations of model capabilities.
Boosting Adversarial Transferability by Achieving Flat Local Maxima
Specifically, we randomly sample an example and adopt a first-order procedure to approximate the Hessian/vector product, which makes computing more efficient by interpolating two neighboring gradients.
Large Language Models are Visual Reasoning Coordinators Liangyu Chen,, Bo Li
Existing methods like ensemble still struggle to aggregate these models with the desired higher-order communications. In this work, we propose Cola, a novel paradigm that coordinates multiple VLMs for visual reasoning.
Diffusion-based Curriculum Reinforcement Learning
V arious approaches have been proposed for the generation of curriculum goals.
OV-PARTS: Towards Open-Vocabulary Part Segmentation (Supplementary Material)
The number of part queries is set to 50. SGD optimizer with the initial learning rate of 2e-2 and weight decay of 5e-4 is used. We sample 128 training samples for each object part class. The initial value of the learnable fusion weight is 0.5 . The total batch size is 8, and the training iterations amount to 40k.