Prior-Fitted and Frozen Scorers for Multimodal Contrastive Learning

arXiv:2610.14770 · cs.LG, cs.AI · Submitted 2026-10-10 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-10-10

Updated: 2026-10-10

Code: https://github.com/Lightning-AI/lightning

Terminology

• Contrastive Learning — 1× in this paper · explained in 6 episodes

Sources

• Learning from Randomly Initialized Neural Network Features
• What to align in multimodal contrastive learning?
• Foundation Models for Causal Inference via Prior-Data Fitted Networks
• Representation Learning via Invariant Causal Mechanisms
• Transformers Can Do Bayesian Inference
• Representation Learning with Contrastive Predictive Coding
• Cohort-Based Active Modality Acquisition
• Beyond Objective Expressivity: Geometry Preservation in Multimodal Contrastive Learning
• Hidden in the Multiplicative Interaction: Uncovering Fragility in Multimodal Contrastive Learning
• Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis
• Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
• TabClustPFN: A Prior-data Fitted Network for Tabular Data Clustering

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