Skip to content
View Masoudjafaripour's full-sized avatar
🎯
Focusing
🎯
Focusing

Highlights

  • Pro

Organizations

@Adaptive-Robotic-Lab

Block or report Masoudjafaripour

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Masoudjafaripour/README.md

I am a grad student in CS at the UofA, supervised by Prof. Osmar Zaiane. My research focuses on multimodal generative models, including LLMs, VLMs, and diffusion models, with emphasis on 3D spatial reasoning. Current work includes scaling spatial and fine-grained visual reasoning in multimodal LLMs (potentially with image generation) with test-time scaling, RL post-training for efficient reasoning with curating customized vision-language datasets.


📊 Current Focus

  • Efficient Spatial & Visual Reasoning with LLMs/VLMs/MMLMs
  • Vision-Language Understanding & Embodied Spatial Reasoning
  • 3D Representations, Grounding, & Space Understanding
  • Building Vision-Language Datasets for Embodied Multi-Agent Systems
  • Visual and Geometry Retrieval Systems

🎓 Academic Background

  • M.Sc. in CS, University of Alberta (Present)
  • Ph.D. in ECE, University of Alberta (Transferred to CS)
  • M.Sc. & B.Sc. in ME, Sharif University of Technology & Univ. of Tehran

💬 Connect with Me

Website Badge Twitter Badge LinkedIn Badge ResearchGate Badge Google Scholar Badge

Pinned Loading

  1. nanochat-VLM nanochat-VLM Public

    A minimal, hackable Vision-Language Model built on Karpathy’s nanochat — add image understanding and multimodal chat for under $200 in compute.

    Python 23 2

  2. Spatial_Reasoning_VLMs Spatial_Reasoning_VLMs Public

    A repo for enhancing spatial reasoning in VLMs using CoT and VoT prompting for 3D visual environments

    Python 12 1

  3. AIFP AIFP Public

    Adaptive Iterative Feedback Prompting for Obstacle-Aware Path Planning via LLMs - LM4Planning - AAAI2025

    Python 9 3

  4. Multimodal_Datasets_Generative_Reasoning Multimodal_Datasets_Generative_Reasoning Public

    A repository for surveying, organizing, and prototyping dataset and benchmark construction pipelines for generative reasoning in multimodal large language models. It focuses on data-centric practic…

    Jupyter Notebook 11

  5. Deep-Learning-Koopman-SSMs-World_Model Deep-Learning-Koopman-SSMs-World_Model Public

    A repo for using different dynamic world modeling for prediction and control: including deep learning based koopman and State-Space Modes (SSM)

    Python 10 2

  6. OnlineRLHF OnlineRLHF Public

    A repo for Implemented online preference-based reward learning under human irrationality & delayed feedback

    Python 8 1