TPAMI 2025 papers on Vision-language and multimodal
72 of the 932 papers published in TPAMI 2025 (7.7%) are on Vision-language and multimodal, compared with 7.4% at TPAMI 2024. They fall into 6 topics.
See TPAMI 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
Cross-modal learning · 27 papers
- MulFS-CAP: Multimodal Fusion-Supervised Cross-Modality Alignment Perception for Unregistered Infrared-Visible Image Fusion (157 citations)
- Uni-MoE: Scaling Unified Multimodal LLMs With Mixture of Experts (136 citations)
- Cross-Modality Distillation for Multi-Modal Tracking (60 citations)
- OmniFuse: Composite Degradation-Robust Image Fusion With Language-Driven Semantics (55 citations)
- FreeFusion: Infrared and Visible Image Fusion via Cross Reconstruction Learning (50 citations)
- Reliable and Balanced Transfer Learning for Generalized Multimodal Face Anti-Spoofing (44 citations)
- RingMoE: Mixture-of-Modality-Experts Multi-Modal Foundation Models for Universal Remote Sensing Image Interpretation (43 citations)
- Tracing Intricate Cues in Dialogue: Joint Graph Structure and Sentiment Dynamics for Multimodal Emotion Recognition (41 citations)
- Learning Probabilistic Presence-Absence Evidence for Weakly-Supervised Audio-Visual Event Perception (39 citations)
- An Efficient Image Fusion Network Exploiting Unifying Language and Mask Guidance (32 citations)
- Learning to Rebalance Multi-Modal Optimization by Adaptively Masking Subnetworks (23 citations)
- Pathway-Aware Multimodal Transformer (PAMT): Integrating Pathological Image and Gene Expression for Interpretable Cancer Survival Analysis (23 citations)
and 15 more in the interactive map.
Multimodal LLMs · 15 papers
- Otter: A Multi-Modal Model With In-Context Instruction Tuning (574 citations)
- Foundation Models Defining a New Era in Vision: A Survey and Outlook (564 citations)
- Mini-Gemini: Mining the Potential of Multi-Modality Vision Language Models (446 citations)
- Toward Visual Grounding: A Survey (82 citations)
- VisionUnite: A Vision-Language Foundation Model for Ophthalmology Enhanced With Clinical Knowledge (33 citations)
- CAT+: Investigating and Enhancing Audio-Visual Understanding in Large Language Models (21 citations)
- The Synergy Between Data and Multi-Modal Large Language Models: A Survey From Co-Development Perspective (17 citations)
- Aligning, Autoencoding and Prompting Large Language Models for Novel Disease Reporting (13 citations)
- RelationLMM: Large Multimodal Model as Open and Versatile Visual Relationship Generalist (13 citations)
- Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning (9 citations)
- New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration (4 citations)
- Synergy of Sight and Semantics: Holistic Visual Understanding With CLIP (3 citations)
and 3 more in the interactive map.
Human and embodied modeling · 12 papers
- Handwritten Text Recognition: A Survey (65 citations)
- Context Perception Parallel Decoder for Scene Text Recognition (54 citations)
- Instruction-Guided Scene Text Recognition (48 citations)
- Understand Layout and Translate Text: Unified Feature-Conductive End-to-End Document Image Translation (8 citations)
- A Learning Paradigm for Selecting Few Discriminative Stimuli in Eye-Tracking Research (5 citations)
- Diagnostic Captioning by Cooperative Task Interactions and Sample-Graph Consistency (4 citations)
- LFSRM: Few-Shot Diagram-Sentence Matching via Local-Feedback Self-Regulating Memory (3 citations)
- A Unified Masked Jigsaw Puzzle Framework for Vision and Language Models (2 citations)
- M$^{3}$3D: A Multimodal, Multilingual and Multitask Dataset for Grounded Document-Level Information Extraction
- BRACTIVE: A Brain Activation Approach to Human Visual Brain Learning
- Improving Generalized Visual Grounding With Instance-Aware Joint Learning
- Semantic Correspondence: Unified Benchmarking and a Strong Baseline
CLIP and zero-shot · 10 papers
- iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval (47 citations)
- Toward a Holistic Evaluation of Robustness in CLIP Models (20 citations)
- Visual-Language Scene-Relation-Aware Zero-Shot Captioner (14 citations)
- Bi-Modality Individual-Aware Prompt Tuning for Visual-Language Model (9 citations)
- Text to Image for Multi-Label Image Recognition With Joint Prompt-Adapter Learning (9 citations)
- Frequency-Based Comprehensive Prompt Learning for Vision-Language Models (7 citations)
- Decouple Before Align: Visual Disentanglement Enhances Prompt Tuning (2 citations)
- Structure-Induced Gradient Regulation for Generalizable Vision-Language Models
- Causal Interventional Prompt Tuning for Few-Shot Out-of-Distribution Generalization
- Scaling up Multimodal Pre-Training for Sign Language Understanding
Robot action and navigation · 4 papers
- NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning (118 citations)
- Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environments (41 citations)
- Hulk: A Universal Knowledge Translator for Human-Centric Tasks (33 citations)
- Toward Accurate Procedure Planning in Instructional Videos: Visual State Generation Helps Task-Selective Diffusion
Visual question answering · 4 papers
- Prophet: Prompting Large Language Models With Complementary Answer Heuristics for Knowledge-Based Visual Question Answering (53 citations)
- Hadamard Product in Deep Learning: Introduction, Advances and Challenges (43 citations)
- Uncertainty-Aware Medical Diagnostic Phrase Identification and Grounding (39 citations)
- Social Reasoning-Aware Trajectory Prediction via Multimodal Language Model (9 citations)
