Multimodal Learning

From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech CVPR 2025 From Fairness to Infinity: Outcome-Indistinguishable (Omni)Prediction in Evolving Graphs COLT 2025 From Generation to Detection: A Multimodal Multi-Task Dataset for Benchmarking Health Misinformation EMNLP 2025 From Grounding to Manipulation: Case Studies of Foundation Model Integration in Embodied Robotic Systems EMNLP 2025 From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration CVPR 2025 From Holistic to Localized: Local Enhanced Adapters for Efficient Visual Instruction Fine-Tuning ICCV 2025 From Introspection to Best Practices: Principled Analysis of Demonstrations in Multimodal In-Context Learning NAACL 2025 From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection ICML 2025 From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinement EMNLP 2025 From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding EMNLP 2025 From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons CVPR 2025 From Observation to Understanding: Front-Door Adjustments with Uncertainty Calibration for Enhancing Egocentric Reasoning in LVLMs ACL 2025 From Panels to Prose: Generating Literary Narratives from Comics ICCV 2025 From Perception to Reasoning: Enhancing Vision-Language Models for Mobile UI Understanding ACL 2025 From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual Modalities ICLR 2025 From Recall to Creation: Generating Follow-Up Questions Using Bloom’s Taxonomy and Grice’s Maxims ACL 2025 From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks NAACL 2025 From Shortcuts to Balance: Attribution Analysis of Speech-Text Feature Utilization in Distinguishing Original from Machine-Translated Texts EMNLP 2025 From Sparse Signal to Smooth Motion: Real-Time Motion Generation with Rolling Prediction Models CVPR 2025 From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities ACL 2025 From Static to Dynamic: Enhancing AAC with Generative Imagery and Zero-Shot TTS Interspeech 2025 From Templates to Natural Language: Generalization Challenges in Instruction-Tuned LLMs for Spatial Reasoning IJCNLP 2025 From Text to Multi-Modal: Advancing Low-Resource-Language Translation through Synthetic Data Generation and Cross-Modal Alignments NAACL 2025 From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining ICML 2025 From Tower to Spire: Adding the Speech Modality to a Translation-Specialist LLM EMNLP 2025