Multimodal Learning

FLAIR: VLM with Fine-grained Language-informed Image Representations CVPR 2025 FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training CVPR 2025 FLAME: Learning to Navigate with Multimodal LLM in Urban Environments AAAI 2025 FLAM: Frame-Wise Language-Audio Modeling ICML 2025 FLARE: A Framework for Stellar Flare Forecasting Using Stellar Physical Properties and Historical Records IJCAI 2025 FlashAudio: Rectified Flow for Fast and High-Fidelity Text-to-Audio Generation ACL 2025 FlashSloth : Lightning Multimodal Large Language Models via Embedded Visual Compression CVPR 2025 Flash-VStream: Efficient Real-Time Understanding for Long Video Streams ICCV 2025 FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding WACV 2025 FLEURS-ASL: Including American Sign Language in Massively Multilingual Multitask Evaluation NAACL 2025 Flexible Frame Selection for Efficient Video Reasoning CVPR 2025 Flexible Thinking for Multimodal Emotional Support Conversation via Reinforcement Learning EMNLP 2025 FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation ACL 2025 FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Models EMNLP 2025 FLIP: Flow-Centric Generative Planning as General-Purpose Manipulation World Model ICLR 2025 FLIQA-AD: a Fusion Model with Large Language Model for Better Diagnose and MMSE Prediction of Alzheimer’s Disease NAACL 2025 F-LMM: Grounding Frozen Large Multimodal Models CVPR 2025 FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait ICCV 2025 FloorPlan-LLaMa: Aligning Architects’ Feedback and Domain Knowledge in Architectural Floor Plan Generation ACL 2025 Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion CVPR 2025 Flow4Agent: Long-form Video Understanding via Motion Prior from Optical Flow ICCV 2025 FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Flow Models CoRL 2025 FlowTok: Flowing Seamlessly Across Text and Image Tokens ICCV 2025 Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens ICLR 2025 FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering EMNLP 2025