Submitted by akhaliq 8 M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning · 12 authors 1
Submitted by akhaliq 8 Ada-TTA: Towards Adaptive High-Quality Text-to-Talking Avatar Synthesis · 8 authors 1
Submitted by akhaliq 2 Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions · 3 authors
Submitted by akhaliq 1 Text-only Domain Adaptation using Unified Speech-Text Representation in Transducer · 5 authors
Submitted by akhaliq 1 Triggering Multi-Hop Reasoning for Question Answering in Language Models using Soft Prompts and Random Walks · 3 authors
Submitted by akhaliq 1 Learning to Ground Instructional Articles in Videos through Narrations · 3 authors