Multimodal Learning

DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation ACL 2026 DSERT-RoLL: Robust Multi-Modal Perception for Diverse Driving Conditions with Stereo Event-RGB-Thermal Cameras, 4D Radar, and Dual-LiDAR CVPR 2026 Dual-Domain Multimodal Hyperbolic Fusion for Cardiopulmonary Disease Diagnosis in Emergency Care WACV 2026 Dynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videos CVPR 2026 Easy2Hard: From Partially to Fully Unmatched Modalities as Negative Samples in Contrastive Learning CVPR 2026 EmoThinker: Advancing Visual-Acoustic Emotion Analysis via Structural Token Selection and Chain-of-Thought Reasoning CVPR 2026 Emotion-Wheel-Guided Audio-Referred Text Representation for Multimodal Emotion Recognition in Conversation ACL 2026 Enhancing Descriptive Captions with Visual Attributes for Multimodal Perception CVPR 2026 Exploring Visual Pretraining for Learning Language Intelligence CVPR 2026 Factorized Context Aggregation for Robust Cancer Risk Estimation via Soft Re-Ranked Retrieval and Hierarchical Anchors CVPR 2026 Factorize, Reconstruct, Enhance: A Unified Framework for Multimodal Sentiment Analysis CVPR 2026 FALCON: False-Negative Aware Learning of Contrastive Negatives in Vision-Language Alignment CVPR 2026 FedAFD: Multimodal Federated Learning via Adversarial Fusion and Distillation CVPR 2026 FineLAP: Taming Heterogeneous Supervision for Fine-grained Language-Audio Pretraining ACL 2026 FlowComposer: Composable Flows for Compositional Zero-Shot Learning CVPR 2026 ForceVLA2: Unleashing Hybrid Force-Position Control with Force Awareness for Contact-Rich Manipulation CVPR 2026 From Experts to Bases: Orthogonal Subspace Mixture for Continual Multimodal Instruction Tuning ACL 2026 From Exploration to Exploitation: A Two-Stage Entropy RLVR Approach for Noise-Tolerant MLLM Training CVPR 2026 From Panel to Pixel: Zoom-In Vision-Language Pretraining from Biomedical Scientific Literature CVPR 2026 From Sparse to Sense-Grounded: Wikipedia Training for Ukrainian Visual-WSD CoNLL 2026 Gau-Occ: Geometry-Completed Gaussians for Multi-Modal 3D Occupancy Prediction CVPR 2026 Gaussian Graphical Learning via PSD Constraint for Blockwise Missing Multimodal Data UAI 2026 GEMCONT: Genetics-based Multimodal Contrastive Learning Enhances Phenotypic embeddings and Boosts Genetic Discovery MIDL 2026 Geometry-Aware Depth-Guided Explainable Multimodal Polyp Size Estimation: A Fusion Model Beyond RGB MIDL 2026 GraspALL: Adaptive Structural Compensation from Illumination Variation for Robotic Garment Grasping in Any Low-Light Conditions CVPR 2026