# R1-Track: Direct Application of MLLMs to Visual Object Tracking via Reinforcement Learning

arXiv: https://arxiv.org/abs/2506.21980 · HTML: https://mlsanity.com/paper/2506.21980/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 19 references that are in the map.
- First posted on arXiv 27 Jun 2025.

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild](https://mlsanity.com/paper/1810.11981/) (2018)
- [SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks](https://mlsanity.com/paper/1812.11703/) (2018)
- [Transformer Tracking](https://mlsanity.com/paper/2103.15436/) (2021)
- [Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework](https://mlsanity.com/paper/2203.11991/) (2022)
- [ECO: Efficient Convolution Operators for Tracking](https://mlsanity.com/paper/1611.09224/) (2016)

## Built on by (most cited first, 9 of 9)

- [OneThinker: All-in-one Reasoning Model for Image and Video](https://mlsanity.com/paper/2512.03043/) (2025)
- [ReasoningTrack: Chain-of-Thought Reasoning for Long-term Vision-Language Tracking](https://mlsanity.com/paper/2508.05221/) (2025)
- [CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning](https://mlsanity.com/paper/2512.19554/) (2025)
- [Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs](https://mlsanity.com/paper/2608.20492/) (2026)
- [Debate-Enhanced Pseudo Labeling and Frequency-Aware Progressive Debiasing for Weakly-Supervised Camouflaged Object Detection with Scribble Annotations](https://mlsanity.com/paper/2512.20260/) (2025)
- [ViewSAM: Learning View-aware Cross-modal Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking](https://mlsanity.com/paper/2605.02638/) (2026)
- [Dynamic Parsing and Updating Natural Language Specification using VLMs for Robust Vision-Language Tracking](https://mlsanity.com/paper/2606.29357/) (2026)
- [VANTAGE-Bench: Evaluating the Infrastructure AI Gap in Vision-Language Models](https://mlsanity.com/paper/2609.09396/) (2026)
- [EventLens: Event-Structure Reinforcement Learning for Video Understanding](https://mlsanity.com/paper/2610.16172/) (2026)

## Abstract (arXiv)

Visual single object tracking aims to continuously localize and estimate the scale of a target in subsequent video frames, given only its initial state in the first frame. This task has traditionally been framed as a template matching problem, evolving through major phases including correlation filters, two-stream networks, and one-stream networks with significant progress achieved. However, these methods typically require explicit classification and regression modeling, depend on supervised training with large-scale datasets, and are limited to the single task of tracking, lacking flexibility. In recent years, multi-modal large language models (MLLMs) have advanced rapidly. Open-source models like Qwen2.5-VL, a flagship MLLMs with strong foundational capabilities, demonstrate excellent performance in grounding tasks. This has spurred interest in applying such models directly to visual tracking. However, experiments reveal that Qwen2.5-VL struggles with template matching between image pairs (i.e., tracking tasks). Inspired by deepseek-R1, we fine-tuned Qwen2.5-VL using the group relative policy optimization (GRPO) reinforcement learning method on a small-scale dataset with a rule-based reward function. The resulting model, R1-Track, achieved notable performance on the GOT-10k benchmark. R1-Track supports flexible initialization via bounding boxes or text descriptions while retaining most of the original model's general capabilities. And we further discuss potential improvements for R1-Track. This rough technical report summarizes our findings as of May 2025.