CogniDual Framework: Self-Training Large Language Models within a Dual-System Theoretical Framework for Improving Cognitive Tasksby…
LMLT: Low-to-high Multi-Level Vision Transformer for Image Super-Resolutionby Jeongsoo Kim, Jongho Nang, Junsuk ChoeFirst submitted…
Boosting Generalizability towards Zero-Shot Cross-Dataset Single-Image Indoor Depth by Meta-Initializationby Cho-Ying Wu, Yiqi Zhong, Junying…
AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Modelsby Qianchi Zhang, Hainan…
Learning in Hybrid Active Inference Modelsby Poppy Collis, Ryan Singh, Paul F Kinghorn, Christopher L…
Path-Consistency: Prefix Enhancement for Efficient Inference in LLMby Jiace Zhu, Yingtao Shen, Jie Zhao, An…
ViRED: Prediction of Visual Relations in Engineering Drawingsby Chao Gu, Ke Lin, Yiyang Luo, Jiahui…
ConCSE: Unified Contrastive Learning and Augmentation for Code-Switched Embeddingsby Jangyeong Jeon, Sangyeon Cho, Minuk Ma,…
VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformersby Juncan Deng, Shuaiting Li, Zeyu Wang, Hong…
Reasoning with maximal consistent signaturesby Matthias Thimm, Jandson Santos Ribeiro SantosFirst submitted to arxiv on:…