Education
Universal Online Learning with Gradient Variations: A Multi-layer Online Ensemble Approach
In this paper, we propose an online convex optimization approach with two different levels of adaptivity. On a higher level, our approach is agnostic to the unknown types and curvatures of the online functions, while at a lower level, it can exploit the unknown niceness of the environments and attain problem-dependent guarantees.
MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention Huiqiang Jiang, Yucheng Li
Existing methods for speeding up pre-filling often fail to maintain acceptable accuracy or efficiency when applied to long-context LLMs.
Virtual Class Enhanced Discriminative Embedding Learning
Binghui Chen, Weihong Deng, Haifeng Shen
Neural Information Processing Systems http://nips.cc/
Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation
Risto Vuorio, Shao-Hua Sun, Hexiang Hu, Joseph J. Lim
Neural Information Processing Systems http://nips.cc/
Predictive Attractor Models
The task of sequential memory is considered challenging for models operating under biological constraints (i.e., local synaptic computations) for many reasons, including catastrophic forgetting,
NetHack is Hard to Hack
In this work, we conduct a comprehensive study of NetHack and examine various learning mechanisms to enhance the performance of neural models.