S squared COPE: Self-Supervised Concept Discovery via Preference Learning
cs.CV
Submitted: 2026-06-12
Updated: 2026-09-27
Project page: https://shilongxiang.github.io/S2COPE
Terminology
Sources
- There Was Never a Bottleneck in Concept Bottleneck Models
- Qwen3-VL Technical Report
- Seeing Beyond Words: Self-Supervised Visual Learning for Multimodal Large Language Models
- PaMi-VDPO: Mitigating Video Hallucinations by Prompt-Aware Multi-Instance Video Preference Learning
- Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
- CLIP-Free, Label Free, Unsupervised Concept Bottleneck Models
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- Visual Jigsaw Post-Training Improves MLLMs
- Qwen3 Technical Report
- Visual Representation Alignment for Multimodal Large Language 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