Lexicon-Level Contrastive Visual-Grounding Improves Language Modelingby Chengxu Zhuang, Evelina Fedorenko, Jacob AndreasFirst submitted to arxiv…
Multi-Modal Hallucination Control by Visual Information Groundingby Alessandro Favero, Luca Zancato, Matthew Trager, Siddharth Choudhary,…
Learning from Synthetic Data for Visual Groundingby Ruozhen He, Ziyan Yang, Paola Cascante-Bonilla, Alexander C.…
Ground-A-Score: Scaling Up the Score Distillation for Multi-Attribute Editingby Hangeol Chang, Jinho Chang, Jong Chul…
VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learningby Yongshuo Zong, Ondrej Bohdal,…
Softened Symbol Grounding for Neuro-symbolic Systemsby Zenan Li, Yuan Yao, Taolue Chen, Jingwei Xu, Chun…
HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decodingby Zhaorun Chen, Zhuokai Zhao, Hongyin Luo, Huaxiu…
Theoretical Foundations of Deep Selective State-Space Modelsby Nicola Muca Cirone, Antonio Orvieto, Benjamin Walker, Cristopher…
Evaluating Very Long-Term Conversational Memory of LLM Agentsby Adyasha Maharana, Dong-Ho Lee, Sergey Tulyakov, Mohit…
Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decodingby Ailin Deng, Zhirui…