IJCV 2026 papers on Vision-language and multimodal
69 of the 477 papers published in IJCV 2026 (14.5%) are on Vision-language and multimodal, compared with 11.7% at IJCV 2025. They fall into 6 topics.
See IJCV 2026 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 · 22 papers
- Lumina-mGPT: Flexible Photorealistic Autoregressive Text-to-Image Generation (155 citations)
- EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning (94 citations)
- Liquid: Language Models are Scalable and Unified Multi-Modal Generators (93 citations)
- TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation (56 citations)
- EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuning (50 citations)
- EgoPlan-Bench2: A Benchmark for Multimodal Large Language Model Planning in Real-World Scenarios (47 citations)
- From Training-Free to Adaptive: Empirical Insights into MLLMs’ Understanding of Detection Information (40 citations)
- A Survey of Medical Vision-and-Language Applications and Their Techniques (33 citations)
- Reasoning Segmentation for Images and Videos: A Survey (18 citations)
- Light-VQA+: A Video Quality Assessment Model for Exposure Correction with Vision-Language Guidance (12 citations)
- Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes (10 citations)
- AdViP: Aligning Multi-modal LLMs via Adaptive Vision-enhanced Preference Optimization (8 citations)
and 10 more in the interactive map.
Cross-modal learning · 16 papers
- Multimodal Alignment and Fusion: A Survey (271 citations)
- Self-Balancing Multimodal Models via Multi-Loss Gradient Modulation (22 citations)
- Human Activity Recognition using RGB-DVS Cameras: A Multi-modal Heat Conduction Model and A Benchmark Dataset (5 citations)
- Is Contrastive Distillation Enough for Learning Comprehensive 3D Representations? (4 citations)
- Knowing Where to Focus: Attention-Guided Alignment for Text-based Person Search (4 citations)
- UMCL: Unimodal-generated Multimodal Contrastive Learning for Cross-compression-rate Deepfake Detection (3 citations)
- Hearing and Seeing Through CLIP: A Framework for Self-Supervised Sound Source Localization (2 citations)
- CAS-AIR-3D: A Large-scale Low-quality Multi-modal Face Database (1 citation)
- Audio-Visual Generation
- Blurring Modal Boundaries: A Unified Survey from Single- to Multi-modal Person Re-ldentification
- IterRF: Iterative and Interpretable Mutual Enhancement for Joint Multi-Modal Image Registration and Fusion
- MICTracker: Modality Informativeness Controlled Multi-modal Fusion for Adaptive RGB-D Visual Tracking
and 4 more in the interactive map.
CLIP and zero-shot · 16 papers
- Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Prompting (26 citations)
- A Closer Look at Conditional Prompt Tuning for Vision-Language Models (20 citations)
- Efficient Test-Time Prompt Tuning for Vision-Language Models (17 citations)
- Adapting Vision-Language Models Without Labels: A Comprehensive Survey (16 citations)
- BayesAdapter: Enhanced Uncertainty Estimation in CLIP Few-Shot Adaptation (9 citations)
- AmPLe: Supporting Vision-Language Models via Adaptive-Debiased Ensemble Multi-Prompt Learning (2 citations)
- Test-Time Computing for Referring Multimodal Large Language Models (1 citation)
- Uniformity Preserving Transfer for Visual Prompt Tuning under Long-tailed Distribution (1 citation)
- A Multi-Modal Knowledge-Driven Approach for Generalized Zero-shot Video Classification
- Adapting Vision-Language Models from Iconic to Inclusive for Multi-label Recognition Without Labels
- Generalized Logit Adjustment: Improved Fine-tuning by Mitigating Label Bias in Zero-Shot Vision Models
- LAMP: Long-Tailed Multi-modal Prompt Tuning for Vision-Language Models
and 4 more in the interactive map.
Human and embodied modeling · 9 papers
- Large Foundation Model Empowered Region-aware Underwater Image Captioning (50 citations)
- Multi-Granularity Prediction with Learnable Fusion for Scene Text Recognition (12 citations)
- A Traditional Approach for Color Constancy and Color Assimilation Illusions with Its Applications to Low-Light Image Enhancement (5 citations)
- Concept-Based Explanation for Deep Vision Models: A Comprehensive Survey on Techniques, Taxonomy, Applications, and Recent Advances (2 citations)
- Fine-Grained Multimodal Alignment for Image-Text Retrieval via Graph Learning (2 citations)
- GLAD: Generative Language-Assisted Visual Tracking for Low-Semantic Templates (2 citations)
- Neuro-Inspired Visual Pattern Recognition via Biological Reservoir Computing (2 citations)
- ELTA 2.0: Rethinking Long-Tail for Image Aesthetics Assessment
- Multimodal Scene Representation using Hypergraph & Map Similarity Measure for Image Localization
Robot action and navigation · 5 papers
- Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving (196 citations)
- TopV-Nav: Unlocking the Top-View Spatial Reasoning Potential of MLLM for Zero-Shot Object Navigation (36 citations)
- GoClick: Lightweight Element Grounding Model for Autonomous GUI Interaction (1 citation)
- Eyegent: Visual Attention Orchestration on Concepts
- PASG-RoboKeyBench: A Closed-Loop Automated Framework and Benchmark for Operation Primitive Extraction and Semantic Anchoring in Robotic Manipulation
