IJCV 2025 papers on Vision-language and multimodal
31 of the 266 papers published in IJCV 2025 (11.7%) are on Vision-language and multimodal, compared with 8.5% at IJCV 2024. They fall into 6 topics.
See IJCV 2025 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Multimodal LLMs · 14 papers
- TokenPacker: Efficient Visual Projector for Multimodal LLM (165 citations)
- SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models (96 citations)
- HiLM-D: Enhancing MLLMs with Multi-scale High-Resolution Details for Autonomous Driving (91 citations)
- Visual Instruction Tuning towards General-Purpose Multimodal Large Language Model: A Survey (49 citations)
- GenderBias-VL: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing (26 citations)
- Attention Reallocation: Towards Zero-cost and Controllable Hallucination Mitigation of MLLMs (24 citations)
- Insect-Foundation: A Foundation Model and Large Multimodal Dataset for Vision-Language Insect Understanding (18 citations)
- Learning with Enriched Inductive Biases for Vision-Language Models (14 citations)
- Clothing Purification with Causality Meets Vision-Language Pretraining Models (8 citations)
- ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning (5 citations)
- MMRL++: Parameter-Efficient and Interaction-Aware Representation Learning for Vision-Language Models (5 citations)
- Vision Generalist Model: A Survey (3 citations)
and 2 more in the interactive map.
Cross-modal learning · 10 papers
- C2RF: Bridging Multi-modal Image Registration and Fusion via Commonality Mining and Contrastive Learning (71 citations)
- Part-Whole Relational Fusion Towards Multi-Modal Scene Understanding (63 citations)
- Multi-Text Guidance Is Important: Multi-Modality Image Fusion via Large Generative Vision-Language Model (61 citations)
- SMLNet: A SPD Manifold Learning Network for Infrared and Visible Image Fusion (10 citations)
- $$\hbox {I}^2$$MD: 3D Action Representation Learning with Inter- and Intra-Modal Mutual Distillation (7 citations)
- Fusion for Visual-Infrared Person ReID in Real-World Surveillance Using Corrupted Multimodal Data (6 citations)
- Modality Confusion Learning: A Versatile Framework for Visible-Infrared Re-identification (4 citations)
- Bayes-CAL: Robust Cross-Modal Alignment by Bayesian Approach for Few-Shot OoD Generalization (3 citations)
- Data-Adaptive Weight-Ensembling for Multi-task Model Fusion (3 citations)
- Learning to Generalize Heterogeneous Representation for Cross-Modality Image Synthesis via Multiple Domain Interventions (1 citation)
CLIP and zero-shot · 4 papers
- Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training (18 citations)
- Supplementary Prompt Learning for Vision-Language Models (4 citations)
- Segment Anything in Context with Vision Foundation Models (3 citations)
- CAT-TPT: Class-Agnostic Text-based Test-time Prompt Tuning for Vision-Language Models (1 citation)
