AAAI 2025 accepted papers on Vision-language and multimodal
297 of the 3,486 papers accepted at AAAI 2025 (8.5%) are on Vision-language and multimodal, compared with 6.9% at AAAI 2024. They fall into 6 topics.
See AAAI 2025 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Human and embodied modeling · 91 papers
- ENCODER: Entity Mining and Modification Relation Binding for Composed Image Retrieval (28 citations)
- Game4Loc: A UAV Geo-Localization Benchmark from Game Data (28 citations)
- BearLLM: A Prior Knowledge-Enhanced Bearing Health Management Framework with Unified Vibration Signal Representation (22 citations)
- Each Fake News Is Fake in Its Own Way: An Attribution Multi-Granularity Benchmark for Multimodal Fake News Detection (21 citations)
- Motion Prior Knowledge Learning with Homogeneous Language Descriptions for Moving Infrared Small Target Detection (21 citations)
- LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extraction (19 citations)
- UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction (17 citations)
- From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach (16 citations)
- StarVector: Generating Scalable Vector Graphics Code from Images and Text (16 citations)
- Improving Multimodal Social Media Popularity Prediction via Selective Retrieval Knowledge Augmentation (14 citations)
- Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints (14 citations)
- AWRaCLe: All-Weather Image Restoration Using Visual In-Context Learning (10 citations)
and 79 more in the interactive map.
Cross-modal learning · 74 papers
- DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis (77 citations)
- Enriching Multimodal Sentiment Analysis Through Textual Emotional Descriptions of Visual-Audio Content (49 citations)
- MENTOR: Multi-level Self-supervised Learning for Multimodal Recommendation (47 citations)
- BSAFusion: A Bidirectional Stepwise Feature Alignment Network for Unaligned Medical Image Fusion (44 citations)
- DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification (30 citations)
- Tokenization, Fusion, and Augmentation: Towards Fine-grained Multi-modal Entity Representation (26 citations)
- MambaPro: Multi-Modal Object Re-identification with Mamba Aggregation and Synergistic Prompt (23 citations)
- CognitionCapturer: Decoding Visual Stimuli from Human EEG Signal with Multimodal Information (19 citations)
- External Reliable Information-enhanced Multimodal Contrastive Learning for Fake News Detection (18 citations)
- RaCMC: Residual-Aware Compensation Network with Multi-Granularity Constraints for Fake News Detection (16 citations)
- RGBT Tracking via All-layer Multimodal Interactions with Progressive Fusion Mamba (16 citations)
- Revisiting Multimodal Fusion for 3D Anomaly Detection from an Architectural Perspective (12 citations)
and 62 more in the interactive map.
Multimodal LLMs · 55 papers
- FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts (58 citations)
- Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference (46 citations)
- Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation (42 citations)
- LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding (36 citations)
- Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference (26 citations)
- Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models (23 citations)
- ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area (21 citations)
- Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback (20 citations)
- Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models (18 citations)
- Enhancing Multimodal Large Language Models Complex Reason via Similarity Computation (17 citations)
- HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models (15 citations)
- UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios (14 citations)
and 43 more in the interactive map.
CLIP and zero-shot · 46 papers
- Enhance Vision-Language Alignment with Noise (42 citations)
- Learning to Prompt with Text Only Supervision for Vision-Language Models (26 citations)
- Standing on the Shoulders of Giants: Reprogramming Visual-Language Model for General Deepfake Detection (22 citations)
- Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation (19 citations)
- DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval (19 citations)
- CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination (16 citations)
- Kernel-Aware Graph Prompt Learning for Few-Shot Anomaly Detection (16 citations)
- Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image Classification (13 citations)
- SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretraining (12 citations)
- Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models (12 citations)
- ViPCap: Retrieval Text-Based Visual Prompts for Lightweight Image Captioning (11 citations)
- ELLA-V: Stable Neural Codec Language Modeling with Alignment-Guided Sequence Reordering (10 citations)
and 34 more in the interactive map.
Visual question answering · 27 papers
- VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis (30 citations)
- Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos (14 citations)
- Interpretable Face Anti-Spoofing: Enhancing Generalization with Multimodal Large Language Models (14 citations)
- Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines (11 citations)
- Evaluating Image Hallucination in Text-to-Image Generation with Question-Answering (8 citations)
- Audio Entailment: Assessing Deductive Reasoning for Audio Understanding (7 citations)
- VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering (6 citations)
- DEQA: Descriptions Enhanced Question-Answering Framework for Multimodal Aspect-Based Sentiment Analysis (5 citations)
- Assessing Modality Bias in Video Question Answering Benchmarks with Multimodal Large Language Models (4 citations)
- Fine-grained Adaptive Visual Prompt for Generative Medical Visual Question Answering (4 citations)
- Defeasible Visual Entailment: Benchmark, Evaluator, and Reward-Driven Optimization (3 citations)
- Explicitly Guided Difficulty-Controllable Visual Question Generation (3 citations)
and 15 more in the interactive map.
Robot action and navigation · 4 papers
- Affordances-Oriented Planning Using Foundation Models for Continuous Vision-Language Navigation (21 citations)
- Enhancing Multi-Robot Semantic Navigation Through Multimodal Chain-of-Thought Score Collaboration (9 citations)
- FloNa: Floor Plan Guided Embodied Visual Navigation (2 citations)
- From Large Language Models to Large Action Models: Reasoning and Planning with Physical World Knowledge