VLM2Rec: Resolving Modality Collapse in Vision-Language Models for Sequential Recommendation
cs.IR, cs.AI
Submitted: 2026-03-18
Updated: 2026-11-02
Terminology
Sources
- GPT-4 Technical Report
- Qwen2.5-VL Technical Report
- Session-based Recommendations with Recurrent Neural Networks
- Adam: A Method for Stochastic Optimization
- See-Saw Modality Balance: See Gradient, and Sew Impaired Vision-Language Balance to Mitigate Dominant Modality Bias
- NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
- Making Text Embedders Few-Shot Learners
- Decoupled Weight Decay Regularization
- Representation Learning with Contrastive Predictive Coding
- Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models
- LLMs are Also Effective Embedding Models: An In-depth Overview
- Diagnosing and Rectifying Vision Models using Language
- InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
- Retrv-R1: A Reasoning-Driven MLLM Framework for Universal and Efficient Multimodal Retrieval
Related papers
- UniRank: Benchmarking Ranking Models for Unified Sequential Modeling and Feature Interaction
- Revisiting Text Ranking in Deep Research
- GateSID: One Gate to Balance Semantic and Collaborative Signals across the Item Lifecycle
- SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce
- GINGER: Spicing Up Graph-Based Vector Search
- Subtraction Gets You More: Gap-Aware Retrieval for Multimodal Multi-Hop QA