When Does Sharing Work? Scaling a Shared SigLIP2 Across Image, Video, Audio, and Audio-Visual Representations
cs.CV, cs.AI
Submitted: 2026-10-20
Updated: 2026-10-20
Terminology
Sources
- Qwen2.5-VL Technical Report
- ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
- Extending Context Window of Large Language Models via Positional Interpolation
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- EVA-CLIP: Improved Training Techniques for CLIP at Scale
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- ActionCLIP: A New Paradigm for Video Action Recognition
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- InternVideo: General Video Foundation Models via Generative and Discriminative Learning
- Meta-Transformer: A Unified Framework for Multimodal Learning
- LLaVA-Video: Video Instruction Tuning With Synthetic Data
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs