Deep Learning
LRM-Zero: Training Large Reconstruction Models with Synthesized Data
Unlike previous 3D datasets (e.g., Objaverse) which are often captured or crafted by humans to approximate real 3D data, Zeroverse completely ignores realistic global semantics but is
WelQrate: Defining the Gold Standard in Small Molecule Drug Discovery Benchmarking
Thus, in this paper, we seek to establish a new gold standard for small molecule drug discovery benchmarking, W elQrate .
Understanding Emergent Abilities of Language Models from the Loss Perspective
In this paper, we propose to study emergent abilities in the lens of pre-training loss, instead of model size or training compute.
Guiding a Diffusion Model with a Bad Version of Itself
The popular classifier-free guidance approach uses an unconditional model to guide a conditional model, leading to simultaneously better prompt alignment and higher-quality images at the cost of reduced variation. These effects seem inherently entangled, and thus hard to control.
Graph Convolutions Enrich the Self-Attention in Transformers!
Details and more visualizations are in Appendices C and D.