Multiobjective Vehicle Routing Optimization with Time Windows: A Hybrid Approach Using Deep Reinforcement Learning and…
Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasksby Antoni Kowalczuk, Jan Dubiński, Atiyeh Ashari Ghomi,…
Rethinking Transformer-based Multi-document Summarization: An Empirical Investigationby Congbo Ma, Wei Emma Zhang, Dileepa Pitawela, Haojie…
Controllable Contextualized Image Captioning: Directing the Visual Narrative through User-Defined Highlightsby Shunqi Mao, Chaoyi Zhang,…
How and where does CLIP process negation?by Vincent Quantmeyer, Pablo Mosteiro, Albert GattFirst submitted to…
MATE: Meet At The Embedding – Connecting Images with Long Textsby Young Kyun Jang, Junmo…
A Transformer-Based Multi-Stream Approach for Isolated Iranian Sign Language Recognitionby Ali Ghadami, Alireza Taheri, Ali…
Diagnosing and Re-learning for Balanced Multimodal Learningby Yake Wei, Siwei Li, Ruoxuan Feng, Di HuFirst…
Constrained Intrinsic Motivation for Reinforcement Learningby Xiang Zheng, Xingjun Ma, Chao Shen, Cong WangFirst submitted…
Deep Attention Driven Reinforcement Learning (DAD-RL) for Autonomous Decision-Making in Dynamic Environmentby Jayabrata Chowdhury, Venkataramanan…