HeGTa: Leveraging Heterogeneous Graph-enhanced Large Language Models for Few-shot Complex Table Understandingby Rihui Jin, Yu…
Multi-Stage Multi-Modal Pre-Training for Automatic Speech Recognitionby Yash Jain, David Chan, Pranav Dheram, Aparna Khare,…
FACTOID: FACtual enTailment fOr hallucInation Detectionby Vipula Rawte, S.M Towhidul Islam Tonmoy, Krishnav Rajbangshi, Shravani…
Multi-Task Learning with Multi-Task Optimizationby Lu Bai, Abhishek Gupta, Yew-Soon OngFirst submitted to arxiv on:…
Enhanced Facet Generation with LLM Editingby Joosung Lee, Jinhong KimFirst submitted to arxiv on: 25…
GraphERE: Jointly Multiple Event-Event Relation Extraction via Graph-Enhanced Event Embeddingsby Haochen Li, Di GengFirst submitted…
ECRC: Emotion-Causality Recognition in Korean Conversation for GCNby J. K. Lee, T. M. ChungFirst submitted…
PathM3: A Multimodal Multi-Task Multiple Instance Learning Framework for Whole Slide Image Classification and Captioningby…
CoTBal: Comprehensive Task Balancing for Multi-Task Visual Instruction Tuningby Yanqi Dai, Zebin You, Dong Jing,…
Mixture-of-LoRAs: An Efficient Multitask Tuning for Large Language Modelsby Wenfeng Feng, Chuzhan Hao, Yuewei Zhang,…