Multimodal Learning

Tokenization Allows Multimodal Large Language Models to Understand, Generate and Edit Architectural Floor Plans CVPR 2026 Token Warping Helps MLLMs Look from Nearby Viewpoints CVPR 2026 TongUI: Internet-Scale Trajectories from Multimodal Web Tutorials for Generalized GUI Agents AAAI 2026 Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA EACL 2026 Top-Down Semantic Refinement for Image Captioning AAAI 2026 TOP-RL: Task-Optimized Progressive Token Pruning with Reinforcement Learning for Vision Language Models AAAI 2026 TouchFormer: A Robust Transformer-based Framework for Multimodal Material Perception AAAI 2026 Toward Multimodal Fake News Detection by Multi-perspective Rationale Generation and Verification AAAI 2026 Towards Authentic Movie Dubbing with Retrieve-Augmented Director-Actor Interaction Learning AAAI 2026 Towards Autonomous UAV Visual Object Search in City Space: Benchmark and Agentic Methodology AAAI 2026 Towards Closed-Loop Embodied Empathy Evolution: Probing LLM-Centric Lifelong Empathic Motion Generation in Unseen Scenarios AAAI 2026 Towards Continually-Evolving AI: Selective and Expandable Multimodal Memory System AAAI 2026 Towards Cross-Modal Preservation, Consistency and Alignment for Privacy-Preserving Visible-Infrared Person Re-Identification CVPR 2026 Towards Fine-Grained Adaptation of CLIP via a Self-Trained Alignment Score WACV 2026 Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training ACL 2026 Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion ACL 2026 Towards Generalist Robot Learning from Internet Video: A Survey (Abstract Reprint) AAAI 2026 Towards GUI Agents: Vision-Language Diffusion Models for GUI Grounding CVPR 2026 Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction CVPR 2026 Towards Multimodal Continual Knowledge Embedding with Modality Forgetting Modulation AAAI 2026 Towards Open-Vocabulary Industrial Defect Understanding with a Large-Scale Multimodal Dataset CVPR 2026 Towards Photorealistic Style Transfer with Multimodal Guidance and Robustness to Content Images in Arbitrary Styles WACV 2026 Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models CVPR 2026 Towards Robust and Interpretable Event–Frame Fusion for Autonomous Driving AAAI 2026 Towards Robust Evaluation of Visual Activity Recognition: Resolving Verb Ambiguity with Sense Clustering EACL 2026