Deep Learning
MemoryFormer: Minimize Transformer Computation by Removing Fully-Connected Layers
However, the model size and corresponding computational complexity are constantly scaled up in pursuit of higher performance.
MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models
In this study, we explore the potential of state space models (SSMs). Direct application of SSMs in gesture synthesis encounters difficulties, which stem primarily from the diverse movement dynamics of various body parts.
Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection
Given the complexities inherent in visual scenes, such as object occlusion, a comprehensive understanding often requires observation from multiple viewpoints. Existing multi-viewpoint object-centric learning methods typically employ random or sequential viewpoint selection strategies.
On the Scalability of GNNs for Molecular Graphs
Equal contribution; order determined alphabetically.
Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
Metacognitive knowledge refers to humans' intuitive knowledge of their own thinking and reasoning processes. Today's best LLMs clearly possess some reasoning
