Eagle SPUR Award winner.
Computer Vision and Multimodal AI Researcher
Ashim Dahal
I'm an undergraduate research assistant at The University of Southern Mississippi. I am employed by Dr. Nick Rahimi at the Cyber Innovation Lab. I have also worked under the advisement of Prof. Bikramjit Banerjee and Prof. Rabab Abdelfattah on topics related to multimodal AI and scene reconstruction.
I like building systems that make visual reasoning cheaper, clearer, and easier to inspect: video QA, Gaussian Splatting, segmentation, image-caption evaluation, and model analysis.
Outside research, I play bansuri, read literature, organize campus developer events, and occasionally write essays fast enough to win trouble.
Recent Dispatches
News
Selected updates in life and research, newest first.
Presenting 1 workshop paper in CVPR
Funded for a Google I/O event.
DCUR Undergraduate Symposium Best Paper on Computational Approach winner.
US Semi-Finalist, Hult Prize.
Finalist, International Researcher of the year, USM.
Awarded a $5,500 DCUR summer research grant for Gaussian Splatting.
Drafted objectives for a $51,000 NASA EPSCoR-funded project led by Dr. Rahimi.
Became Lead Organizer of Google Developer Groups (GDG) On Campus at USM.
Became Research Liaison for the School of Computing Sciences and Computer Engineering Student Ambassadors.
Received a $500 Checkpoint award to build an XR application for dyslexia.
Won Best Local Project and Global Nomination at NASA Space Apps Challenge.
Selected Publications
Research
A few Selected works, ordered newest first. Rows with the acid side mark are computer vision and multimodal highlights; click thumbnails to open larger previews.
TwinSim: A Digital Twin based Framework for Sim2Real Robot Policy Training
We Propose a digital twin based robotic simulation framework for sim2real robot policy training. The robot ingests the views from gaussians plats directly as its policy inputs and its low poly digital twin maintains physics and contact logic.
arxiv coming soon
2026
POVQA: Preference-Optimized Video Question Answering with Rationales for Data Efficiency
Making video question answering possible on large context scenes with minimal input tokens.
CVPR Workshop (Proceedings Track)
2026
Does Anchor Selection Matter in 4D Gaussian Streaming?
We study and evaluate anchor selection strategies in 4D Gaussian streaming, demonstrating their impact on performance and efficiency.
arXiv
2026
Embedding Shift Dissection on CLIP: Effects of Augmentations on VLM's Representation Learning
A short paper on how CLIP representations shift under different augmentation strengths and types.
CVPR Workshop (Proceedings Track)
2025
Heuristical Comparison of Vision Transformers Against Convolutional Neural Networks for Semantic Segmentation on Remote Sensing Imagery
A comparison of ViTs and CNNs on iSAID segmentation, including a loss function that helps a smaller CNN compete with a much larger ViT.
IEEE Sensors Journal
2025
Impact Factor 4.5
Redemption Score: A Multi-Modal Evaluation Framework for Image Captioning via Distributional, Perceptual, and Linguistic Signal Triangulation
A robust framework to evaluate image-text pairs under perceptual, semantic, pragmatic, and distributional alignment.
arXiv
2025
Efficiency Bottlenecks of Convolutional Kolmogorov-Arnold Networks: A Comprehensive Scrutiny with ImageNet, AlexNet, LeNet and Tabular Classification
A study of convolutional Kolmogorov-Arnold networks across ImageNet, MNIST, and tabular classification settings.
arXiv
2025
Miscellaneous
Blogs and Paper Summaries
Teaching in Bootcamps
Invited Talks
Teaching in Academia