Multimodal Learning

To Ask or Not to Ask? Detecting Absence of Information in Vision and Language Navigation WACV 2025 TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision ICCV 2025 Token Activation Map to Visually Explain Multimodal LLMs ICCV 2025 TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm WACV 2025 Token-Efficient VLM: High-Resolution Image Understanding via Dynamic Region Proposal ICCV 2025 TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation CVPR 2025 TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization CVPR 2025 Tokenization, Fusion, and Augmentation: Towards Fine-grained Multi-modal Entity Representation AAAI 2025 Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination Mitigation EMNLP 2025 Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem? ACL 2025 ToM-SSI: Evaluating Theory of Mind in Situated Social Interactions EMNLP 2025 ToneCraft: Cantonese Lyrics Generation with Harmony of Tones and Pitches EMNLP 2025 Tonguescape: Exploring Language Models Understanding of Vowel Articulation NAACL 2025 ToolVQA: A Dataset for Multi-step Reasoning VQA with External Tools ICCV 2025 Topological Signatures of Adversaries in Multimodal Alignments ICML 2025 TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model CVPR 2025 Touch2Shape: Touch-Conditioned 3D Diffusion for Shape Exploration and Reconstruction CVPR 2025 ToVE: Efficient Vision-Language Learning via Knowledge Transfer from Vision Experts ICLR 2025 Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment ICLR 2025 Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage ICML 2025 Towards AI-Assisted Psychotherapy: Emotion-Guided Generative Interventions EMNLP 2025 Towards All-in-One Medical Image Re-Identification CVPR 2025 Towards a Multimodal Large Language Model with Pixel-Level Insight for Biomedicine AAAI 2025 Towards an Automated Framework to Audit Youth Safety on TikTok EMNLP 2025 Towards Audio-Visual Navigation in Noisy Environments: A Large-Scale Benchmark Dataset and an Architecture Considering Multiple Sound-Sources AAAI 2025