Multimodal Learning

V-ALPHASOCIAL: Benchmark and Self-Reflective Chain-of-Thought Generation for Visual Social Commonsense Reasoning ACL 2025 Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media Contexts ACL 2025 Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers ICCV 2025 VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs NAACL 2025 VAQUUM: Are Vague Quantifiers Grounded in Visual Data? ACL 2025 VarCMP: Adapting Cross-Modal Pre-Training Models for Video Anomaly Retrieval AAAI 2025 VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification CVPR 2025 VCapAV: A Video-Caption Based Audio-Visual Deepfake Detection Dataset Interspeech 2025 VCD: A Dataset for Visual Commonsense Discovery in Images ACL 2025 VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text ICLR 2025 VCRMNER: Visual Cue Refinement in Multimodal NER using CLIP Prompts COLING 2025 VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents CVPR 2025 VE-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment AAAI 2025 Vector Grimoire: Codebook-based Shape Generation under Raster Image Supervision ICML 2025 Vector-ICL: In-context Learning with Continuous Vector Representations ICLR 2025 VEGAS: Towards Visually Explainable and Grounded Artificial Social Intelligence AAAI 2025 VEHME: A Vision-Language Model For Evaluating Handwritten Mathematics Expressions EMNLP 2025 VELA: An LLM-Hybrid-as-a-Judge Approach for Evaluating Long Image Captions EMNLP 2025 Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval Interspeech 2025 VELOCITI: Benchmarking Video-Language Compositional Reasoning with Strict Entailment CVPR 2025 VENUS: A VLLM-driven Video Content Discovery System for Real Application Scenarios EMNLP 2025 VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models CVPR 2025 Verbalized Representation Learning for Interpretable Few-Shot Generalization ICCV 2025 VerbalTS: Generating Time Series from Texts ICML 2025 VERITAS: Leveraging Vision Priors and Expert Fusion to Improve Multimodal Data EMNLP 2025