Oceania
ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification Y efei He
KV cache compression seeks to discern the saliency of tokens, preserving vital information while aggressively compressing those of less importance.
Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning David Y unis TTI-Chicago Chicago, IL
Exploration in sparse-reward reinforcement learning (RL) is difficult due to the need for long, coordinated sequences of actions in order to achieve any reward.
Knowledge Composition using Task Vectors with Learned Anisotropic Scaling Frederic Z. Zhang Paul Albert
Listed order was determined by a coin toss.
Chain-of-Thought Reasoning without Prompting
These methods, while effective, often involve manually intensive prompt engineering.
Terra: A Multimodal Spatio-Temporal Dataset Spanning the Earth Wei Chen
Since the inception of our planet, the meteorological environment, as reflected through spatio-temporal data, has always been a fundamental factor influencing human life, socio-economic progress, and ecological conservation.
cPAPERS: A Dataset of Situated and Multimodal Interactive Conversations in Scientific Papers
Besides textual paragraphs, researchers rely on various modalities to describe research methods. Figures convey information about concepts developed throughout the paper.