Omni-Embed-Mini: Binding Modalities Without Forgetting via Dense Distillation
cs.CV
Submitted: 2026-10-01
Updated: 2026-10-01
Terminology
Sources
- BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs
- Qwen2-Audio Technical Report
- Think Then Embed: Generative Context Improves Multimodal Embedding
- Scaling up masked audio encoder learning for general audio classification
- MAEB: Massive Audio Embedding Benchmark
- Natural Language Supervision for General-Purpose Audio Representations
- LoRA: Low-Rank Adaptation of Large Language Models
- RzenEmbed: Towards Comprehensive Multimodal Retrieval
- Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
- What If We Recaption Billions of Web Images with LLaMA-3?
- VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents
- Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini
- GSQA: An End-to-End Model for Generative Spoken Question Answering
- BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
- EmbeddingGemma: Powerful and Lightweight Text Representations
- HeySQuAD: A Spoken Question Answering Dataset
- C-Pack: Packed Resources For General Chinese Embeddings
- Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
- Omni-Embed-Nemotron: A Unified Multimodal Retrieval Model for Text, Image, Audio, and Video
- Jasper and Stella: distillation of SOTA embedding models
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