Unbundling Multimodal Vision Encoding
cs.CV, cs.LG
Submitted: 2026-11-12
Updated: 2026-11-12
Project page: https://unbundling.github.io
Terminology
Sources
- Layer Normalization
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- PaliGemma: A versatile 3B VLM for transfer
- Chameleon: Mixed-Modal Early-Fusion Foundation Models
- How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model
- Gemma 4 Technical Report
- Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes
- Gaussian Error Linear Units (GELUs)
- Scaling Laws for Neural Language Models
- Kimi K2.5: Visual Agentic Intelligence
- Kimi K3: Open Frontier Intelligence
- MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts
- DeepSeek-VL: Towards Real-World Vision-Language Understanding
- Mono-InternVL-1.5: Towards Cheaper and Faster Monolithic Multimodal Large Language Models
- Muse Glimmer 30B: An On-Device Agentic Model
- Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
- NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
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