Multimodal Learning

AutoPresent: Designing Structured Visuals from Scratch CVPR 2025 AVAM: a Universal Training-free Adaptive Visual Anchoring Embedded into Multimodal Large Language Model for Multi-image Question Answering ICCV 2025 AV-Flow: Transforming Text to Audio-Visual Human-like Interactions ICCV 2025 AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models ICLR 2025 A Video-grounded Dialogue Dataset and Metric for Event-driven Activities AAAI 2025 A Video is Worth 10000 Words: Training and Benchmarking with Diverse Captions for Better Long Video Retrieval WACV 2025 A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets ICCV 2025 A-VL: Adaptive Attention for Large Vision-Language Models AAAI 2025 AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMs ICCV 2025 A Wander Through the Multimodal Landscape: Efficient Transfer Learning via Low-rank Sequence Multimodal Adapter AAAI 2025 AWRaCLe: All-Weather Image Restoration Using Visual In-Context Learning AAAI 2025 AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents ACL 2025 BabyVLM: Data-Efficient Pretraining of VLMs Inspired by Infant Learning ICCV 2025 Backdooring Vision-Language Models with Out-Of-Distribution Data ICLR 2025 BACON: Improving Clarity of Image Captions via Bag-of-Concept Graphs CVPR 2025 BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models CVPR 2025 Balance-Aware Sequence Sampling Makes Multi-Modal Learning Better IJCAI 2025 BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing ICML 2025 Balancing User-Item Structure and Interaction with Large Language Models and Optimal Transport for Multimedia Recommendation IJCAI 2025 BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games ICLR 2025 BanglaTalk: Towards Real-Time Speech Assistance for Bengali Regional Dialects AACL 2025 BanHateME : Understanding Hate in Bangla Memes thorough Detection, Categorization, and Target Profiling AACL 2025 BANMIME : Misogyny Detection with Metaphor Explanation on Bangla Memes EMNLP 2025 BannerAgency: Advertising Banner Design with Multimodal LLM Agents EMNLP 2025 BannerBench: Benchmarking Vision Language Models for Multi-Ad Selection with Human Preferences EMNLP 2025