Multimodal Learning

Stress-Testing Multimodal Foundation Models for Crystallographic Reasoning ACL 2025 SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation CVPR 2025 Symmetrical Visual Contrastive Optimization: Aligning Vision-Language Models with Minimal Contrastive Images ACL 2025 SyncVP: Joint Diffusion for Synchronous Multi-Modal Video Prediction CVPR 2025 Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation CVPR 2025 T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting CVPR 2025 TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models ICCV 2025 TaiwanVQA: A Benchmark for Visual Question Answering for Taiwanese Daily Life COLING 2025 Taking Notes Brings Focus? Towards Multi-Turn Multimodal Dialogue Learning EMNLP 2025 Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation ICCV 2025 Task-Aware Resolution Optimization for Visual Large Language Models EMNLP 2025 Task-driven Image Fusion with Learnable Fusion Loss CVPR 2025 Task-Gated Multi-Expert Collaboration Network for Degraded Multi-Modal Image Fusion ICML 2025 Teaching VLMs to Localize Specific Objects from In-context Examples ICCV 2025 Team ML_Forge@DravidianLangTech 2025: Multimodal Hate Speech Detection in Dravidian Languages NAACL 2025 TemCoCo: Temporally Consistent Multi-modal Video Fusion with Visual-Semantic Collaboration ICCV 2025 Testing Spatial Intuitions of Humans and Large Language and Multimodal Models in Analogies ACL 2025 Text Embedding is Not All You Need: Attention Control for Text-to-Image Semantic Alignment with Text Self-Attention Maps CVPR 2025 Texts or Images? A Fine-grained Analysis on the Effectiveness of Input Representations and Models for Table Question Answering ACL 2025 The_Deathly_Hallows@DravidianLangTech 2025: Multimodal Hate Speech Detection in Dravidian Languages NAACL 2025 Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoning EMNLP 2025 Thermal-Aware Low-Light Image Enhancement: A Real-World Benchmark and a New Light-Weight Model AAAI 2025 The Source Image is the Best Attention for Infrared and Visible Image Fusion ICCV 2025 TIV-Diffusion: Towards Object-Centric Movement for Text-driven Image to Video Generation AAAI 2025 Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation ICCV 2025