PPLqa: An Unsupervised Information-Theoretic Quality Metric for Comparing Generative Large Language Modelsby Gerald Friedland, Xin…
StreetviewLLM: Extracting Geographic Information Using a Chain-of-Thought Multimodal Large Language Modelby Zongrong Li, Junhao Xu,…
Advancing Complex Medical Communication in Arabic with Sporo AraSum: Surpassing Existing Large Language Modelsby Chanseo…
Improved GUI Grounding via Iterative Narrowingby Anthony NguyenFirst submitted to arxiv on: 18 Nov 2024CategoriesMain:…
A Novel Approach to Eliminating Hallucinations in Large Language Model-Assisted Causal Discoveryby Grace Sng, Yanming…
LaVida Drive: Vision-Text Interaction VLM for Autonomous Driving with Token Selection, Recovery and Enhancementby Siwen…
Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehensionby Yongdong Luo, Xiawu Zheng, Xiao Yang, Guilin Li, Haojia…
Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learningby Xudong Yan, Songhe Feng, Yang…
CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMsby Zhehan Kan, Ce Zhang,…
PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignmentby Zhendong Liu, Yuanbi Nie, Yingshui Tan,…