Evaluating Theory of (an uncertain) Mind: Predicting the Uncertain Beliefs of Others in Conversation Forecastingby…
Multi-Modal Generative AI: Multi-modal LLM, Diffusion and Beyondby Hong Chen, Xin Wang, Yuwei Zhou, Bin…
ViBERTgrid BiLSTM-CRF: Multimodal Key Information Extraction from Unstructured Financial Documentsby Furkan Pala, Mehmet Yasin Akpınar,…
Generalizing monocular colonoscopy image depth estimation by uncertainty-based global and local fusion networkby Sijia Du,…
Inference-Friendly Models With MixAttentionby Shashank Rajput, Ying Sheng, Sean Owen, Vitaliy ChileyFirst submitted to arxiv…
Analogous Alignments: Digital “Formally” meets Analogby Hansa Mohanty, Deepak Narayan GaddeFirst submitted to arxiv on:…
Generative LLM Powered Conversational AI Application for Personalized Risk Assessment: A Case Study in COVID-19by…
Brotherhood at WMT 2024: Leveraging LLM-Generated Contextual Conversations for Cross-Lingual Image Captioningby Siddharth Betala, Ishan…
Depression Diagnosis Dialogue Simulation: Self-improving Psychiatrist with Tertiary Memoryby Kunyao Lan, Bingrui Jin, Zichen Zhu,…
Enhancing Scientific Reproducibility Through Automated BioCompute Object Creation Using Retrieval-Augmented Generation from Publicationsby Sean Kim,…