| Treble Counterfactual VLMs: A Causal Approach to Hallucination | Mar 8, 2025 | Autonomous Drivingcounterfactual | CodeCode Available | 0 |
| Integrating Frequency-Domain Representations with Low-Rank Adaptation in Vision-Language Models | Mar 8, 2025 | Caption GenerationQuestion Answering | —Unverified | 0 |
| SplatTalk: 3D VQA with Gaussian Splatting | Mar 8, 2025 | 3DGSQuestion Answering | —Unverified | 0 |
| MoEMoE: Question Guided Dense and Scalable Sparse Mixture-of-Expert for Multi-source Multi-modal Answering | Mar 8, 2025 | Answer GenerationMixture-of-Experts | —Unverified | 0 |
| Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model | Mar 6, 2025 | General KnowledgeImage Captioning | CodeCode Available | 2 |
| Enhancing SAM with Efficient Prompting and Preference Optimization for Semi-supervised Medical Image Segmentation | Mar 6, 2025 | Active LearningImage Segmentation | —Unverified | 0 |
| AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM | Mar 6, 2025 | Anomaly DetectionLanguage Modeling | CodeCode Available | 2 |
| Question-Aware Gaussian Experts for Audio-Visual Question Answering | Mar 6, 2025 | Audio-visual Question AnsweringAudio-Visual Question Answering (AVQA) | CodeCode Available | 1 |
| Enhancing Vietnamese VQA through Curriculum Learning on Raw and Augmented Text Representations | Mar 5, 2025 | Question AnsweringVisual Question Answering | CodeCode Available | 0 |
| OWLViz: An Open-World Benchmark for Visual Question Answering | Mar 4, 2025 | Question AnsweringVisual Question Answering | —Unverified | 0 |
| BioD2C: A Dual-level Semantic Consistency Constraint Framework for Biomedical VQA | Mar 4, 2025 | Medical DiagnosisQuestion Answering | CodeCode Available | 0 |
| Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models | Mar 3, 2025 | MemorizationQuestion Answering | CodeCode Available | 0 |
| FunBench: Benchmarking Fundus Reading Skills of MLLMs | Mar 2, 2025 | AnatomyBenchmarking | —Unverified | 0 |
| CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering | Mar 1, 2025 | Continual LearningLanguage Modeling | —Unverified | 0 |
| Fine-Grained Retrieval-Augmented Generation for Visual Question Answering | Feb 28, 2025 | Question AnsweringRAG | —Unverified | 0 |
| MedHallTune: An Instruction-Tuning Benchmark for Mitigating Medical Hallucination in Vision-Language Models | Feb 28, 2025 | Decision MakingHallucination | CodeCode Available | 0 |
| Can Large Language Models Unveil the Mysteries? An Exploration of Their Ability to Unlock Information in Complex Scenarios | Feb 27, 2025 | Data IntegrationQuestion Answering | —Unverified | 0 |
| MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning | Feb 26, 2025 | Domain GeneralizationMedical Image Analysis | —Unverified | 0 |
| Talking to the brain: Using Large Language Models as Proxies to Model Brain Semantic Representation | Feb 26, 2025 | Question Answeringvalid | —Unverified | 0 |
| Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference | Feb 25, 2025 | Question AnsweringRAG | CodeCode Available | 0 |
| FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA | Feb 25, 2025 | Question AnsweringRetrieval | —Unverified | 0 |
| MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs | Feb 24, 2025 | Question AnsweringVisual Question Answering | CodeCode Available | 3 |
| All-in-one: Understanding and Generation in Multimodal Reasoning with the MAIA Benchmark | Feb 24, 2025 | AllMultimodal Reasoning | —Unverified | 0 |
| Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines | Feb 23, 2025 | Answer GenerationLanguage Modeling | —Unverified | 0 |
| Tracking the Copyright of Large Vision-Language Models through Parameter Learning Adversarial Images | Feb 23, 2025 | Adversarial AttackQuestion Answering | —Unverified | 0 |
