Architecture-Dependent Fusion Pathways in MLLMs

cs.LG

Submitted: 2026-10-02

Updated: 2026-10-02

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• GPT-4 Technical Report
• MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• The Platonic Representation Hypothesis
• Aligning Multimodal Representations through an Information Bottleneck
• SOLO: A Single Transformer for Scalable Vision-Language Modeling
• DINOv2: Learning Robust Visual Features without Supervision
• Revisiting the Platonic Representation Hypothesis: An Aristotelian View

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks