PACE: Progressive Angular-to-Norm Contrastive Embedding
cs.CV, cs.AI, cs.CL, cs.LG
Submitted: 2026-09-14
Updated: 2026-09-14
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- When Does Embedding Magnitude Matter? A Cross-Task Functional-Symmetry Framework
- E5-V: Universal Embeddings with Multimodal Large Language Models
- Gemini Embedding: Generalizable Embeddings from Gemini
- Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
- GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation
- Token-level Data Selection for Safe LLM Fine-tuning
- Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini
- EVA-CLIP: Improved Training Techniques for CLIP at Scale
- SalQ-VLM: Fine-Grained Saliency-Guided Quantization for Vision-Language Models
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
- Flash-VAED: Plug-and-Play VAE Decoders for Efficient Video Generation
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