Search Results for author:
Found 5 papers, 3 papers with code
Parameter-Inverted Image Pyramid Networks
Our core idea is to use models with different parameter sizes to process different resolution levels of the image pyramid, thereby balancing computational efficiency and performance.
Synergizing Spatial Optimization with Large Language Models for Open-Domain Urban Itinerary Planning
Our system, deployed on an online platform, has attracted thousands of users for their urban travel planning.
Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft
Many reinforcement learning environments (e. g., Minecraft) provide only sparse rewards that indicate task completion or failure with binary values.
Video Background Music Generation: Dataset, Method and Evaluation
We believe our dataset, benchmark model, and evaluation metric will boost the development of video background music generation.
Confidence-aware Non-repetitive Multimodal Transformers for TextCaps
Our CNMT consists of a reading, a reasoning and a generation modules, in which Reading Module employs better OCR systems to enhance text reading ability and a confidence embedding to select the most noteworthy tokens.
