AI Wiki — Knowledge Base

Benchmarking Linguistic Adaptation in Comparable-Sized LLMs: A Study of Llama-3.1-8B, Mistral-7B-v0.1, and Qwen3-8B on Romanized Nepali

arXiv:2604.14171v1 Announce Type: new Abstract: Romanized Nepali, the Nepali language written in the Latin alphabet, is the dominant medium for informal digital communication in Nepal, yet it remains

model-releasesarxiv-cs-cl

17 Apr 2026

Search: “tesla”

TESLA: Taylor Expansion of Sinusoidal Learnable Activations

Machine Learning-Based Classification of Jhana Advanced Concentrative Absorption Meditation Using 7 Tesla Functional Magnetic Resonance Imaging

Cephalonauts One: A deep fMRI dataset for decoding naturalistic speech in the human brain

Capacitive Touchscreens at Risk: Recovering Handwritten Trajectory on Smartphone via Electromagnetic Emanations

Energy Variation in Training Modern Computer Vision Architectures

RoboGPU: Accelerating GPU Collision Detection for Robotics

EcoBoat: Design and Experimental Validation of an Autonomous Body-Board Boat For Cleaning Water Bodies

Dancing Stick Figures: An Introductory Dataset for Training Video Generation Models

FoldPipe: Bounded Remote Streaming of Native Molecular Shards with Asynchronous Prefetch

Parameter-Efficient pretrained-CT-to-MRI Transfer for Rectal Cancer Segmentation: Performance-Calibration Trade-offs

Pedagogical AI in Mental Health: A Tri-Stream Fine-Tuned LLM Framework for Automated Clinical Supervision and Risk Triage

TransNRank: Towards Accurate Neoantigen Ranking with Transformer

SkySeaLand: A Wide-Format Satellite Transportation Benchmark with an Ultra-Lightweight Detection Baseline

Sensitivity Analysis of GRU, LSTM and Transformer Encoder in Classification of Automated Driving Systems

Cumsum-Composable Phase Transport for Low-Cost Streaming Keyword Spotting

Fin-Analyst at FinMMEval 2026 Task 3: A Live Hybrid Trading Agent with LLM Specialists and Rule-Based Signals

InferNet: Exploiting Aggregate GPU Profiles as Side-Channel for DNN Architecture Inference

GPU Parallelization Strategies for Forward and Backward Propagation in Shallow Neural Networks: A CUDA-Based Comparative Study

Performance Analysis of YOLOv11 and YOLOv8 for Mixed Traffic Object Detection under Adverse Weather Conditions in Developing Countries

Helicase: Uncertainty-Guided Supply Chain Knowledge Graph Construction with Autonomous Multi-Agent LLMs

Are Large Language Models Economically Viable for Industry Deployment?

SMILE-UHURA Challenge -- Small Vessel Segmentation at Mesoscopic Scale from Ultra-High Resolution 7T Magnetic Resonance Angiograms

Benchmarking Linguistic Adaptation in Comparable-Sized LLMs: A Study of Llama-3.1-8B, Mistral-7B-v0.1, and Qwen3-8B on Romanized Nepali

Coherence in the brain unfolds across separable temporal regimes