# ProfVLM: A lightweight video-language model for multi-view proficiency estimation

arXiv: https://arxiv.org/abs/2509.26278 · HTML: https://mlsanity.com/paper/2509.26278/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 34 of its 56 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Image editing and quality assessment](https://mlsanity.com/mllm/image-editing-and-quality-assessment/)

## Builds on (most cited first, 30 of 34)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [VideoBERT: A Joint Model for Video and Language Representation Learning](https://mlsanity.com/paper/1904.01766/) (2019)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [VideoAgent: Long-form Video Understanding with Large Language Model as Agent](https://mlsanity.com/paper/2403.10517/) (2024)
- [Revisiting Skeleton-based Action Recognition](https://mlsanity.com/paper/2104.13586/) (2021)
- [SmolVLM: Redefining small and efficient multimodal models](https://mlsanity.com/paper/2504.05299/) (2025)
- [Project Aria: A New Tool for Egocentric Multi-Modal AI Research](https://mlsanity.com/paper/2308.13561/) (2023)
- [VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset](https://mlsanity.com/paper/2304.08345/) (2023)
- [What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment](https://mlsanity.com/paper/1904.04346/) (2019)
- [EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World](https://mlsanity.com/paper/2403.16182/) (2024)
- [Apollo: An Exploration of Video Understanding in Large Multimodal Models](https://mlsanity.com/paper/2412.10360/) (2024)
- [Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision](https://mlsanity.com/paper/2407.06189/) (2024)
- [Skating-Mixer: Long-Term Sport Audio-Visual Modeling with MLPs](https://mlsanity.com/paper/2203.03990/) (2022)
- [A Comprehensive Survey of Action Quality Assessment: Method and Benchmark](https://mlsanity.com/paper/2412.11149/) (2024)
- [Narrative Action Evaluation with Prompt-Guided Multimodal Interaction](https://mlsanity.com/paper/2404.14471/) (2024)
- [BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation](https://mlsanity.com/paper/2503.20781/) (2025)
- [egoPPG: Heart Rate Estimation from Eye-Tracking Cameras in Egocentric Systems to Benefit Downstream Vision Tasks](https://mlsanity.com/paper/2502.20879/) (2025)
- [Towards AI-Powered Video Assistant Referee System (VARS) for Association Football](https://mlsanity.com/paper/2407.12483/) (2024)
- [Tracking Skiers from the Top to the Bottom](https://mlsanity.com/paper/2312.09723/) (2023)

## Built on by (most cited first, 4 of 4)

- [Parameter-Efficient Multi-View Proficiency Estimation: From Discriminative Classification to Generative Feedback](https://mlsanity.com/paper/2605.03848/) (2026)
- [SkillMoV: Mixture-of-View Routing with Prototype-Conditioned Gating for Unified Multi-View Proficiency Estimation](https://mlsanity.com/paper/2606.17615/) (2026)
- [Divide, Deliberate, Decide: A Multi-Agent Framework for Fine-Grained Egocentric Action Recognition](https://mlsanity.com/paper/2606.17627/) (2026)
- [SkillSpotter: Pose-Aware Multi-View Skilled Action Detection and Grading in Ego-Exo Videos](https://mlsanity.com/paper/2606.31127/) (2026)

## Abstract (arXiv)

Most existing approaches formulate action quality assessment and skill proficiency estimation as discriminative prediction tasks, typically producing discrete labels or scores without explicitly modeling the reasoning process underlying the assessment. We instead reformulate the problem as generative vision-language modeling, introducing ProfVLM, a parameter-efficient vision-language model that jointly predicts proficiency levels and generates expert-like natural language feedback from multi-view videos. ProfVLM leverages conditional language generation to provide actionable insights along with quantitative evaluation scores. Central to our method is an AttentiveGatedProjector that dynamically fuses and projects multi-view egocentric and exocentric features from a frozen TimeSformer backbone into a language model fine-tuned for feedback generation. Trained on EgoExo4D with expert commentaries, ProfVLM surpasses state-of-the-art methods while using up to 20x fewer parameters and reducing training time by up to 60% compared to existing classification-based methods. By providing natural language critiques aligned with performance levels, this work shows that generative vision-language modeling offers a powerful and efficient paradigm shift for interpretable action quality assessment.