8 papers
Transferable Delay-Aware Reinforcement Learning via Implicit Causal Graph Modeling
Chenran Zhao, Dianxi Shi, Yaowen Zhang +2
Random delays weaken the temporal correspondence between actions and subsequent state feedback, making it difficult for agents to identify the true propagation process of action ef…
Delay-Empowered Causal Hierarchical Reinforcement Learning
Chenran Zhao, Dianxi Shi, Haotian Wang +4
Many real-world tasks involve delayed effects, where the outcomes of actions emerge after varying time lags. Existing delay-aware reinforcement learning methods often rely on state…
CEIDM: A Controlled Entity and Interaction Diffusion Model for Enhanced Text-to-Image Generation
Mingyue Yang, Dianxi Shi, Jialu Zhou +4
In Text-to-Image (T2I) generation, the complexity of entities and their intricate interactions pose a significant challenge for T2I method based on diffusion model: how to effectiv…
Dynamic Embedding of Hierarchical Visual Features for Efficient Vision-Language Fine-Tuning
Xinyu Wei, Guoli Yang, Jialu Zhou +4
Large Vision-Language Models (LVLMs) commonly follow a paradigm that projects visual features and then concatenates them with text tokens to form a unified sequence input for Large…
Separation and Collaboration: Two-Level Routing Grouped Mixture-of-Experts for Multi-Domain Continual Learning
Jialu Zhou, Dianxi Shi, Shaowu Yang +5
Multi-Domain Continual Learning (MDCL) acquires knowledge from sequential tasks with shifting class sets and distribution. Despite the Parameter-Efficient Fine-Tuning (PEFT) method…
UniCT Depth: Event-Image Fusion Based Monocular Depth Estimation with Convolution-Compensated ViT Dual SA Block
Luoxi Jing, Dianxi Shi, Zhe Liu +5
Depth estimation plays a crucial role in 3D scene understanding and is extensively used in a wide range of vision tasks. Image-based methods struggle in challenging scenarios, whil…