3 papers
cs.NE2026
Rethinking Pairwise Token Interaction in Spiking Transformers
Sicheng Shen, Dongcheng Zhao, Zhiyuan Li +5
Spiking Transformers inherit token interaction mechanisms from conventional Transformers, yet their sparse binary representations fundamentally alter how token-to-token communicati…
cs.LG2024
Learning Causal Dynamics Models in Object-Oriented Environments
Zhongwei Yu, Jingqing Ruan, Dengpeng Xing
Causal dynamics models (CDMs) have demonstrated significant potential in addressing various challenges in reinforcement learning. To learn CDMs, recent studies have performed causa…
cs.AI2023
Learning Top-k Subtask Planning Tree based on Discriminative Representation Pre-training for Decision Making
Jingqing Ruan, Kaishen Wang, Qingyang Zhang +2
Many complicated real-world tasks can be broken down into smaller, more manageable parts, and planning with prior knowledge extracted from these simplified pieces is crucial for hu…