Multimodal Learning

Look before You Leap: Dual Logical Verification for Knowledge-based Visual Question Generation COLING 2024 LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate NeurIPS 2024 LRM-Zero: Training Large Reconstruction Models with Synthesized Data NeurIPS 2024 Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models NeurIPS 2024 M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models EMNLP 2024 MACAROON: Training Vision-Language Models To Be Your Engaged Partners EMNLP 2024 MAFA: Managing False Negatives for Vision-Language Pre-training CVPR 2024 Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification CVPR 2024 Make Pixels Dance: High-Dynamic Video Generation CVPR 2024 MaPPER: Multimodal Prior-guided Parameter Efficient Tuning for Referring Expression Comprehension EMNLP 2024 MAR: Matching-Augmented Reasoning for Enhancing Visual-based Entity Question Answering EMNLP 2024 Matching Anything by Segmenting Anything CVPR 2024 MEANT: Multimodal Encoder for Antecedent Information EMNLP 2024 Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models NeurIPS 2024 MICap: A Unified Model for Identity-Aware Movie Descriptions CVPR 2024 MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing ACL 2024 Mitigating Object Hallucination via Concentric Causal Attention NeurIPS 2024 Mitigating Open-Vocabulary Caption Hallucinations EMNLP 2024 MmAP: Multi-Modal Alignment Prompt for Cross-Domain Multi-Task Learning AAAI 2024 MM-WLAuslan: Multi-View Multi-Modal Word-Level Australian Sign Language Recognition Dataset NeurIPS 2024 MoDE: CLIP Data Experts via Clustering CVPR 2024 Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representations CVPR 2024 MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric CVPR 2024 MoReVQA: Exploring Modular Reasoning Models for Video Question Answering CVPR 2024 MSPE: Multi-Scale Patch Embedding Prompts Vision Transformers to Any Resolution NeurIPS 2024