VaME: Exploring Variational Latent Reasoning for Multimodal Embeddings
cs.CV
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- TTE-Flash: Accelerating Reasoning-based Multimodal Representations via Think-Then-Embed Tokens
- Think Then Embed: Generative Context Improves Multimodal Embedding
- Implicit Chain of Thought Reasoning via Knowledge Distillation
- PLUME: Latent Reasoning Based Universal Multimodal Embedding
- RzenEmbed: Towards Comprehensive Multimodal Retrieval
- Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings
- E5-V: Universal Embeddings with Multimodal Large Language Models
- LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval
- Auto-Encoding Variational Bayes
- LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning
- UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation
- The information bottleneck method
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control
- UniIR: Training and Benchmarking Universal Multimodal Information Retrievers
- Beyond Chain-of-Thought: Rewrite as a Universal Interface for Generative Multimodal Embeddings
- LaME: Learning to Think in Latent Space for Multimodal Embedding via Information Bottleneck
- TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddings
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models