GitHub

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

In vision-language models (VLMs), visual tokens usually consume a significant amount of computational overhead, despite their sparser information density compared to text tokens. To address this, ...
note

Zero Blender Skills | I Created 4 Geometric Wall Decor Patterns Using 'Rule-Based Shapes' (Escher-style Tile Collection, 3D Print Ready)

*I (mim2026) am a side-hustling dad raising twins. I use AI (Claude) to operate Blender and create 3D models without any prior programming experience (I haven't written a single line of code). I am ...
IEEE

Model-Free Control of Magnetic Microrobotic Swarm for On-Demand Pattern Spreading

Abstract: Introducing collective control strategies to microrobots provides a promising tool for enhancing the capability of individual microrobots and promoting the manipulation performance. However, ...
IEEE

Data-Driven Insights Into EV Charging Patterns: Machine Learning Models Reveal Key Predictors of Station Utilization in Tennessee

Abstract: This study analyzes electric vehicle (EV) charging patterns and station utilization in Tennessee using machine learning (ML) techniques. While previous research has examined time series ...