Multimodal Learning

Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers EMNLP 2025 Language Model Can Listen While Speaking AAAI 2025 Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models EMNLP 2025 Language-to-Space Programming for Training-Free 3D Visual Grounding EMNLP 2025 Large Language Models Are Natural Video Popularity Predictors ACL 2025 Large Multi-modal Models Can Interpret Features in Large Multi-modal Models ICCV 2025 Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding ICLR 2025 Large-scale Pre-training for Grounded Video Caption Generation ICCV 2025 Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability EMNLP 2025 LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior ICLR 2025 Latent Distribution Decouple for Uncertain-Aware Multimodal Multi-label Emotion Recognition ACL 2025 Latent Expression Generation for Referring Image Segmentation and Grounding ICCV 2025 LATTE: Improving Latex Recognition for Tables and Formulae with Iterative Refinement AAAI 2025 LATTE: Learning to Think with Vision Specialists EMNLP 2025 LaVA-Man: Learning Visual Action Representations for Robot Manipulation CoRL 2025 Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations EMNLP 2025 LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models CVPR 2025 LC-Eval: A Bilingual Multi-Task Evaluation Benchmark for Long-Context Understanding EMNLP 2025 Learnable Expansion of Graph Operators for Multi-Modal Feature Fusion ICLR 2025 Learnable Retrieval Enhanced Visual-Text Alignment and Fusion for Radiology Report Generation ICCV 2025 Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning ICML 2025 Learning 4D Panoptic Scene Graph Generation from Rich 2D Visual Scene CVPR 2025 Learning an Implicit Physics Model for Image-based Fluid Simulation ICCV 2025 Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval CVPR 2025 Learning Beyond Still Frames: Scaling Vision-Language Models with Video ICCV 2025