Oceania
Continual Learning for Instruction Following from Realtime Feedback
We evaluate through thousands of human-agent interactions, demonstrating 15.4% absolute improvement in instruction execution accuracy
4f550cb7b30b59553e50cd08a9dbf068-Paper-Conference.pdf
To address this issue, we propose a novel rectification technique via refactoring the projection from 3D to 2D Gaussians.
Limiting Extrapolation in Linear Approximate Value Iteration
Andrea Zanette, Alessandro Lazaric, Mykel J. Kochenderfer, Emma Brunskill
Neural Information Processing Systems http://nips.cc/
Referring Human Pose and Mask Estimation in the Wild Bo Miao
This new task holds significant potential for human-centric applications such as assistive robotics and sports analysis.
Aligning Individual and Collective Objectives in Multi-Agent Cooperation
Among the research topics in multi-agent learning, mixed-motive cooperation is one of the most prominent challenges, primarily due to the mismatch between individual and collective goals.
Neural Tangent Kernel: Convergence and Generalization in Neural Networks
Arthur Jacot, Franck Gabriel, Clement Hongler
This kernel is central to describe the generalization features ofANNs.
The Parameterized Complexity of Cascading Portfolio Scheduling
Eduard Eiben, Robert Ganian, Iyad Kanj, Stefan Szeider
Neural Information Processing Systems http://nips.cc/
Curvilinear Distance Metric Learning
Shuo Chen, Lei Luo, Jian Yang, Chen Gong, Jun Li, Heng Huang
Neural Information Processing Systems http://nips.cc/
