# EgoVLM: Policy Optimization for Egocentric Video Understanding

arXiv: https://arxiv.org/abs/2506.03097 · HTML: https://mlsanity.com/paper/2506.03097/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 22 of its 30 references that are in the map.
- First posted on arXiv 3 Jun 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 22 of 22)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [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)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [Reasoning Models Can Be Effective Without Thinking](https://mlsanity.com/paper/2504.09858/) (2025)
- [MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning](https://mlsanity.com/paper/2502.19634/) (2025)
- [R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model](https://mlsanity.com/paper/2503.05132/) (2025)
- [EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning](https://mlsanity.com/paper/2312.06722/) (2023)
- [VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI](https://mlsanity.com/paper/2410.11623/) (2024)
- [MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA](https://mlsanity.com/paper/2410.07177/) (2024)
- [ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos](https://mlsanity.com/paper/2503.12542/) (2025)
- [Dual-Difficulty Curriculum Learning for Direct Preference Optimization](https://mlsanity.com/paper/2504.07856/) (2025)

## Built on by (most cited first, 12 of 12)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [Object Detection with Multimodal Large Vision-Language Models: An In-depth Review](https://mlsanity.com/paper/2508.19294/) (2025)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges](https://mlsanity.com/paper/2511.13261/) (2025)
- [Robot Learning from Human Videos: A Survey](https://mlsanity.com/paper/2604.27621/) (2026)
- [EgoVITA: Learning to Plan and Verify for Egocentric Video Reasoning](https://mlsanity.com/paper/2511.18242/) (2025)
- [Pro2Assist: Continuous Step-aware Proactive Assistance with Multi-modal Egocentric Perception for Long-horizon Procedural Tasks](https://mlsanity.com/paper/2605.04227/) (2026)
- [EgoProceVQA: A Novel Egocentric Procedural Understanding Task with Self-Skill-Exploration Agent](https://mlsanity.com/paper/2607.13792/) (2026)
- [EgoLoc: A Generalizable Solution for Temporal Interaction Localization in Egocentric Videos](https://mlsanity.com/paper/2508.12349/) (2025)
- [EgoIntent: A Pre-Outcome Micro-Step Benchmark for Understanding What, Why, and Next](https://mlsanity.com/paper/2603.12147/) (2026)
- [Incentivizing Temporal-Awareness in Egocentric Video Understanding Models](https://mlsanity.com/paper/2603.27184/) (2026)
- [Towards Context-Aware Clinical Motion Understanding in Daily Living at Home: Freezing of Gait Detection with Egocentric Vision](https://mlsanity.com/paper/2608.13283/) (2026)

## Abstract (arXiv)

Emerging embodied AI applications, such as wearable cameras and autonomous agents, have underscored the need for robust reasoning from first person video streams. We introduce EgoVLM, a vision-language model specifically designed to integrate visual comprehension and spatial-temporal reasoning within egocentric video contexts. EgoVLM is fine-tuned via Group Relative Policy Optimization (GRPO), a reinforcement learning method adapted to align model outputs with human-like reasoning steps. Following DeepSeek R1-Zero's approach, we directly tune using RL without any supervised fine-tuning phase on chain-of-thought (CoT) data. We evaluate EgoVLM on egocentric video question answering benchmarks and show that domain-specific training substantially improves performance over general-purpose VLMs. Our EgoVLM-3B, trained exclusively on non-CoT egocentric data, outperforms the base Qwen2.5-VL 3B and 7B models by 14.33 and 13.87 accuracy points on the EgoSchema benchmark, respectively. By explicitly generating reasoning traces, EgoVLM enhances interpretability, making it well-suited for downstream applications. Furthermore, we introduce a novel keyframe-based reward that incorporates salient frame selection to guide reinforcement learning optimization. This reward formulation opens a promising avenue for future exploration in temporally grounded egocentric reasoning.