HEED: Density-Weighted Residual Alignment for Hybrid Vision-Language Model Distillation
cs.CV, cs.CL
Submitted: 2026-05-16
Updated: 2026-11-15
Project page: https://sharegpt4o.github.io
Terminology
Sources
- Qwen3-VL Technical Report
- Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models
- Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- LLaVA-OneVision: Easy Visual Task Transfer
- Multimodal Mamba: Decoder-only Multimodal State Space Model via Quadratic to Linear Distillation
- Kosmos-2: Grounding Multimodal Large Language Models to the World
- GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
- An Empirical Study of Mamba-based Language Models
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
- LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models
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