CoVisco: Codec-Native Vision Encoder with Native Token Compression for Unified Image-Video Understanding
cs.CV, cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/ernie-research/CoVisco
Terminology
Sources
- Qwen3-VL Technical Report
- Token Merging: Your ViT But Faster
- LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?
- RzenEmbed: Towards Comprehensive Multimodal Retrieval
- VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks
- Kimi-VL Technical Report
- CLIPA-v2: Scaling CLIP Training with 81.1% Zero-shot ImageNet Accuracy within a \$10,000 Budget; An Extra \$4,000 Unlocks 81.8% Accuracy
- VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents
- EVA-CLIP: Improved Training Techniques for CLIP at Scale
- OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- Demystifying CLIP Data
- Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model
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