Free the Language Model From the Vision Encoder: Semantic Serialization as a Perception Interface for Small Language Models
cs.RO, cs.CL, cs.CV
Submitted: 2026-08-29
Updated: 2026-08-29
Code: https://github.com/ultralytics/ultralytics
Terminology
Sources
- Qwen2.5-VL Technical Report
- Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- Chameleon: Mixed-Modal Early-Fusion Foundation Models
- Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
- Qwen2.5 Technical Report
- Qwen3 Technical Report
- Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- The Llama 3 Herd of Models
- Patch Policy: Efficient Embodied Control via Dense Visual Representations
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving