# Enhancing Lightweight Vision Language Models through Group Competitive Learning for Socially Compliant Navigation

arXiv: https://arxiv.org/abs/2603.11447 · HTML: https://mlsanity.com/paper/2603.11447/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 12 Mar 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [TinyViT: Fast Pretraining Distillation for Small Vision Transformers](https://mlsanity.com/paper/2207.10666/) (2022)
- [Core Challenges of Social Robot Navigation: A Survey](https://mlsanity.com/paper/2103.05668/) (2021)
- [SILC: Improving Vision Language Pretraining with Self-Distillation](https://mlsanity.com/paper/2310.13355/) (2023)
- [SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples](https://mlsanity.com/paper/2312.00825/) (2023)
- [VLM-Social-Nav: Socially Aware Robot Navigation through Scoring using Vision-Language Models](https://mlsanity.com/paper/2404.00210/) (2024)
- [Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation](https://mlsanity.com/paper/2412.01694/) (2024)
- [FedMKT: Federated Mutual Knowledge Transfer for Large and Small Language Models](https://mlsanity.com/paper/2406.02224/) (2024)
- [OLiVia-Nav: An Online Lifelong Vision Language Approach for Mobile Robot Social Navigation](https://mlsanity.com/paper/2409.13675/) (2024)
- [Rethinking Social Robot Navigation: Leveraging the Best of Two Worlds](https://mlsanity.com/paper/2309.13466/) (2023)
- [VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models](https://mlsanity.com/paper/2503.07575/) (2025)
- [Adversarial Contrastive Learning via Asymmetric InfoNCE](https://mlsanity.com/paper/2207.08374/) (2022)
- [AMD: Automatic Multi-step Distillation of Large-scale Vision Models](https://mlsanity.com/paper/2407.04208/) (2024)
- [Interactive Navigation in Environments with Traversable Obstacles Using Large Language and Vision-Language Models](https://mlsanity.com/paper/2310.08873/) (2023)
- [Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning](https://mlsanity.com/paper/2410.01529/) (2024)
- [Multimodal Spatial Language Maps for Robot Navigation and Manipulation](https://mlsanity.com/paper/2506.06862/) (2025)
- [SocialNav-MoE: A Mixture-of-Experts Vision Language Model for Socially Compliant Navigation with Reinforcement Fine-Tuning](https://mlsanity.com/paper/2512.14757/) (2025)
- [From Obstacles to Etiquette: Robot Social Navigation with VLM-Informed Path Selection](https://mlsanity.com/paper/2602.09002/) (2026)
- [ImpedanceGPT: VLM-driven Impedance Control of Swarm of Mini-drones for Intelligent Navigation in Dynamic Environment](https://mlsanity.com/paper/2503.02723/) (2025)
- [MUSON: A Reasoning-oriented Multimodal Dataset for Socially Compliant Navigation in Urban Environments](https://mlsanity.com/paper/2512.22867/) (2025)
- [MAction-SocialNav: Multi-Action Socially Compliant Navigation via Reasoning-enhanced Prompt Tuning](https://mlsanity.com/paper/2512.21722/) (2025)
- [Reinforcement Learning via Auxiliary Task Distillation](https://mlsanity.com/paper/2406.17168/) (2024)
- [Toward Socially Aware Vision-Language Models: Evaluating Cultural Competence Through Multimodal Story Generation](https://mlsanity.com/paper/2508.16762/) (2025)

## Abstract (arXiv)

Social robot navigation requires a sophisticated integration of scene semantics and human social norms. Scaling up Vision Language Models (VLMs) generally improves reasoning and decision-making capabilities for socially compliant navigation. However, increased model size incurs substantial computational overhead, limiting suitability for real-time robotic deployment. Conversely, lightweight VLMs enable efficient inference but often exhibit weaker reasoning and decision-making performance in socially complex environments. Achieving both strong reasoning ability and efficiency remains an open challenge. To bridge this gap, we propose Group Competitive Learning (GCL), a strategy designed to amplify the capabilities of lightweight VLMs. Our strategy introduces the Group Competitive Objective (GCO) to harmonize global semantics with distributional regularization, alongside Asymmetric Group Optimization (AGO) to explore the upper limits of model performance. Empirical evaluations on social navigation benchmarks demonstrate that GCL significantly elevates VLM performance. Specifically, GCL enables the Qwen2.5-VL-3B learner model and guide Qwen3-VL-4B to achieve an F1 score of 0.968 and 0.914, representing 40% and 12% improvement over vanilla supervised fine-tuning (SFT). Notably, under vanilla SFT, the 3B model initially trails the 8B model (F1: 0.692 vs. 0.755). However, through the GCL, the 3B model outperforms (28%) the 8B baseline model. These results suggest that GCL provides an effective solution for achieving both high accuracy and computational efficiency in real-world deployment.