Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Contentby Qiuheng Wang,…
LatteCLIP: Unsupervised CLIP Fine-Tuning via LMM-Synthetic Textsby Anh-Quan Cao, Maximilian Jaritz, Matthieu Guillaumin, Raoul de…
Increasing the Difficulty of Automatically Generated Questions via Reinforcement Learning with Synthetic Preferenceby William Thorne,…
KRAG Framework for Enhancing LLMs in the Legal Domainby Nguyen Ha Thanh, Ken SatohFirst submitted…
When and Where Did it Happen? An Encoder-Decoder Model to Identify Scenario Contextby Enrique Noriega-Atala,…
COMMA: A Communicative Multimodal Multi-Agent Benchmarkby Timothy Ossowski, Jixuan Chen, Danyal Maqbool, Zefan Cai, Tyler…
Diversified and Adaptive Negative Sampling on Knowledge Graphsby Ran Liu, Zhongzhou Liu, Xiaoli Li, Hao…
A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasksby Hoin Jung, Taeuk Jang,…
Moyun: A Diffusion-Based Model for Style-Specific Chinese Calligraphy Generationby Kaiyuan Liu, Jiahao Mei, Hengyu Zhang,…
MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimizationby Yougang Lyu, Lingyong Yan, Zihan Wang, Dawei…