TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Abilityby…
Thai Financial Domain Adaptation of THaLLE – Technical Reportby KBTG Labs, Atthakorn Petchsod, Pornchanan Balee,…
GPT as ghostwriter at the White Houseby Jacques SavoyFirst submitted to arxiv on: 27 Nov…
VLM-HOI: Vision Language Models for Interpretable Human-Object Interaction Analysisby Donggoo Kang, Dasol Jeong, Hyunmin Lee,…
Fine-Tuning LLMs with Noisy Data for Political Argument Generation and Post Guidanceby Svetlana Churina, Kokil…
TopV-Nav: Unlocking the Top-View Spatial Reasoning Potential of MLLM for Zero-shot Object Navigationby Linqing Zhong,…
When Babies Teach Babies: Can student knowledge sharing outperform Teacher-Guided Distillation on small datasets?by Srikrishna…
RAMIE: Retrieval-Augmented Multi-task Information Extraction with Large Language Models on Dietary Supplementsby Zaifu Zhan, Shuang…
ReWind: Understanding Long Videos with Instructed Learnable Memoryby Anxhelo Diko, Tinghuai Wang, Wassim Swaileh, Shiyan…
PPLqa: An Unsupervised Information-Theoretic Quality Metric for Comparing Generative Large Language Modelsby Gerald Friedland, Xin…