Multimodal Learning

MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens ACL 2025 MNLP@DravidianLangTech 2025: A Deep Multimodal Neural Network for Hate Speech Detection in Dravidian Languages NAACL 2025 MNLP@DravidianLangTech 2025: Transformer-based Multimodal Framework for Misogyny Meme Detection NAACL 2025 MobileViCLIP: An Efficient Video-Text Model for Mobile Devices ICCV 2025 MotionDiff: Training-free Zero-shot Interactive Motion Editing via Flow-assisted Multi-view Diffusion ICCV 2025 MPBR: Multimodal Progressive Bidirectional Reasoning for Open-Set Fine-Grained Recognition ICCV 2025 MTGA: Multi-View Temporal Granularity Aligned Aggregation for Event-Based Lip-Reading AAAI 2025 MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering ACL 2025 MUCAR: Benchmarking Multilingual Cross-Modal Ambiguity Resolution for Multimodal Large Language Models EMNLP 2025 Multilingual Pretraining for Pixel Language Models EMNLP 2025 Multi-modal and Multi-scale Spatial Environment Understanding for Immersive Visual Text-to-Speech AAAI 2025 Multi-Modal Framing Analysis of News EMNLP 2025 Multimodal Language Models See Better When They Look Shallower EMNLP 2025 Multi-modal Multi-platform Person Re-Identification: Benchmark and Method ICCV 2025 Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models NAACL 2025 Multimodal Neural Machine Translation: A Survey of the State of the Art EMNLP 2025 Multi-Modal Synergistic Implicit Image Enhancement for Efficient Optical Flow Estimation CVPR 2025 Multimodal Transformers are Hierarchical Modal-wise Heterogeneous Graphs ACL 2025 Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints AAAI 2025 MUST: The First Dataset and Unified Framework for Multispectral UAV Single Object Tracking CVPR 2025 MVL-SIB: A Massively Multilingual Vision-Language Benchmark for Cross-Modal Topical Matching ACL 2025 Not Only Vision: Evolve Visual Speech Recognition via Peripheral Information ICCV 2025 Now You See Me: Context-Aware Automatic Audio Description WACV 2025 Oasis: One Image is All You Need for Multimodal Instruction Data Synthesis ICCV 2025 OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval ACL 2025