Cover Image

Think Then Embed: Generative Context Improves Multimodal Embedding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cui, Xuanming, Cheng, Jianpeng, Chen, Hong-you, Shukla, Satya Narayan, Awasthi, Abhijeet, Pan, Xichen, Ahuja, Chaitanya, Mishra, Shlok Kumar, Yang, Yonghuan, Xiao, Jun, Guo, Qi, Lim, Ser-Nam, Singh, Aashu, Fan, Xiangjun
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TTE-Flash: Accelerating Reasoning-based Multimodal Representations via Think-Then-Embed Tokens
by: Cheng, Jianpeng, et al.
Published: (2026)

Reason to Contrast: A Cascaded Multimodal Retrieval Framework
by: Cui, Xuanming, et al.
Published: (2025)

Unifying Contrastive and Generative Objectives for Visual Understanding and Text-to-Image Generation
by: Li, Chao, et al.
Published: (2026)

StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding
by: Yang, Yanlai, et al.
Published: (2025)

Xray-Visual Models: Scaling Vision models on Industry Scale Data
by: Mishra, Shlok, et al.
Published: (2026)

Transfer between Modalities with MetaQueries
by: Pan, Xichen, et al.
Published: (2025)

AirSketch: Generative Motion to Sketch
by: Lim, Hui Xian Grace, et al.
Published: (2024)

Socratic Students: Teaching Language Models to Learn by Asking Questions
by: Ambati, Rajeev Bhatt, et al.
Published: (2025)

What can Off-the-Shelves Large Multi-Modal Models do for Dynamic Scene Graph Generation?
by: Cui, Xuanming, et al.
Published: (2025)

CompCap: Improving Multimodal Large Language Models with Composite Captions
by: Chen, Xiaohui, et al.
Published: (2024)

A Simple and Effective Reinforcement Learning Method for Text-to-Image Diffusion Fine-tuning
by: Gupta, Shashank, et al.
Published: (2025)

Heteroscedastic Temporal Variational Autoencoder For Irregular Time Series
by: Shukla, Satya Narayan, et al.
Published: (2021)

Towards Chunk-Wise Generation for Long Videos
by: Zhang, Siyang, et al.
Published: (2024)

Cultural and Historical Identity in Amitav Ghosh’s River of Smoke: A Postcolonial Perspective
by: Satya Narayan
Published: (2021)

Depicting Culture and Identity in Amitav Ghosh’s The Shadow Lines
by: Satya Narayan
Published: (2017)

Cultural and Historical Identity in Amitav Ghosh’s River of Smoke: A Postcolonial Perspective
by: Satya Narayan
Published: (2021)

Pooling Attention: Evaluating Pretrained Transformer Embeddings for Deception Classification
by: Mamtani, Sumit, et al.
Published: (2025)

An Attribute-Based Measure of Video Complexity
by: Sarkar, Aditya, et al.
Published: (2026)

TractoEmbed: Modular Multi-level Embedding framework for white matter tract segmentation
by: Goel, Anoushkrit, et al.
Published: (2024)

VideoMerge: Towards Training-free Long Video Generation
by: Zhang, Siyang, et al.
Published: (2025)

Video Decomposition Prior: A Methodology to Decompose Videos into Layers
by: Shrivastava, Gaurav, et al.
Published: (2024)

Is Cosine-Similarity of Embeddings Really About Similarity?
by: Steck, Harald, et al.
Published: (2024)

Realised Volatility Forecasting: Machine Learning via Financial Word Embedding
by: Rahimikia, Eghbal, et al.
Published: (2021)

Beyond Generation: Unlocking Universal Editing via Self-Supervised Fine-Tuning
by: Chen, Harold Haodong, et al.
Published: (2024)

Robust Learning of Diverse Code Edits
by: Aggarwal, Tushar, et al.
Published: (2025)

Effective Embedding of Integer Linear Inequalities for Variational Quantum Algorithms
by: Hess, Maximilian, et al.
Published: (2024)

Self-Adaptive Reconstruction with Contrastive Learning for Unsupervised Sentence Embeddings
by: Liu, Junlong, et al.
Published: (2024)

On Global Embedding of Assisted Fibre Inflation
by: Leontaris, George K., et al.
Published: (2026)

DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflow
by: Long, Tao, et al.
Published: (2025)

Embedding Empirical Distributions for Computing Optimal Transport Maps
by: Jiang, Mingchen, et al.
Published: (2025)

TRACE: Grounding Time Series in Context for Multimodal Embedding and Retrieval
by: Chen, Jialin, et al.
Published: (2025)

LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision
by: Huang, Jiani, et al.
Published: (2023)

DreamMask: Boosting Open-vocabulary Panoptic Segmentation with Synthetic Data
by: Tu, Yuanpeng, et al.
Published: (2025)

Towards Unified 3D Object Detection via Algorithm and Data Unification
by: Li, Zhuoling, et al.
Published: (2024)

Composing Object Relations and Attributes for Image-Text Matching
by: Pham, Khoi, et al.
Published: (2024)

Fast Encoding and Decoding for Implicit Video Representation
by: Chen, Hao, et al.
Published: (2024)

Mitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuning
by: Park, Dongmin, et al.
Published: (2024)

Scene Co-pilot: Procedural Text to Video Generation with Human in the Loop
by: Qian, Zhaofang, et al.
Published: (2024)

Delta Activations: A Representation for Finetuned Large Language Models
by: Xu, Zhiqiu, et al.
Published: (2025)

PianoBind: A Multimodal Joint Embedding Model for Pop-piano Music
by: Bang, Hayeon, et al.
Published: (2025)