Multimodal Learning

Now You Hear Me: Audio Narrative Attacks Against Large Audio–Language Models EACL 2026 O3SLM: Open Weight, Open Data, and Open Vocabulary Sketch-Language Model AAAI 2026 ObjChangeVR: Object State Change Reasoning from Continuous Egocentric Views in VR Environments EACL 2026 ObjecTok: Learning Holistic and Robust Object Tokens for MLLMs AAAI 2026 OCR or Not? Rethinking Document Information Extraction in the MLLMs Era with Real-World Large-Scale Datasets EACL 2026 OIDA-QA: A Multimodal Benchmark for Analyzing the Opioid Industry Documents Archive AAAI 2026 Omni2Sound: Towards Unified Video-Text-to-Audio Generation CVPR 2026 Omni-Attack: Adversarial Attacks on Open-Ended VQA in Black-Box Multimodal LLMs CVPR 2026 OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination AAAI 2026 Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval ACL 2026 Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection CVPR 2026 OmniFM: Toward Modality-Robust and Task-Agnostic Federated Learning for Heterogeneous Medical Imaging CVPR 2026 OmniGen2: Towards Instruction-Aligned Multimodal Generation CVPR 2026 OmniGround: A Comprehensive Spatio-Temporal Grounding Benchmark for Real-World Complex Scenarios CVPR 2026 Omni-I2C: A Holistic Benchmark for High-Fidelity Image-to-Code Generation ACL 2026 Omni IIE Bench: Benchmarking the Practical Capabilities of Image Editing Models CVPR 2026 OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens CVPR 2026 Omni-MMSI: Toward Identity-attributed Social Interaction Understanding CVPR 2026 OmniPT: Unleashing the Potential of Large Vision Language Models for Pedestrian Tracking and Understanding AAAI 2026 Omni-RewardBench: Toward a Comprehensive Evaluation of Generative Reward Models Across Modalities ACL 2026 OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models CVPR 2026 OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation CVPR 2026 One-shot Portrait Stylizaiton via Geometric Alignment WACV 2026 One Single Hub Text Breaks CLIP: Identifying Vulnerabilities in Cross-Modal Encoders via Hubness ACL 2026 OneSug: The Unified End-to-End Generative Framework for E-commerce Query Suggestion AAAI 2026