Africa
Rethinking Exploration in Reinforcement Learning with Effective Metric-Based Exploration Bonus
Additionally, methods that utilize the bisimulation metric for evaluating state discrepancies face a theory-practice gap due to improper approximations in metric learning, particularly struggling with hard exploration tasks.
ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splatting
Omnidirectional (or 360-degree) images are increasingly being used for 3D applications since they allow the rendering of an entire scene with a single image.
Efficient Minimum Bayes Risk Decoding using Low-Rank Matrix Completion Algorithms
First, we empirically show that the scores matrices indeed have a low-rank structure.
The State of Data Curation at NeurIPS: An Assessment of Dataset Development Practices in the Datasets and Benchmarks Track The State of Data Curation at NeurIPS: Appendix A. Rubric 2
A Spoken Language Dataset of Descriptions for Speech - Based Gro unded Language Learning.
The State of Data Curation at NeurIPS: An Assessment of Dataset Development Practices in the Datasets and Benchmarks Track
Data curation is a field with origins in librarianship and archives, whose scholarship and thinking on data issues go back centuries, if not millennia.
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.