Showcase Papers

Every paper below was generated entirely by e5o — from a single topic prompt to a complete research manuscript with real experiments.

📊

Curriculum Learning with Adaptive Difficulty Scheduling for Image Classification

Computer Vision Coming Soon

Investigates adaptive curriculum learning strategies on CIFAR-10/100 benchmarks. Proposes a difficulty-aware scheduling mechanism that dynamically adjusts training sample ordering to improve convergence speed and final accuracy.

💬

Prompt-Length-Aware Routing for Mixture-of-LoRA Experts in Instruction-Following

NLP / PEFT Coming Soon

Proposes a routing mechanism for Mixture-of-LoRA experts that considers prompt length characteristics. Fine-tunes Qwen-2.5-3B with QLoRA to demonstrate improved instruction-following across varying input lengths.

🧬

Graph Attention Networks with Learnable Edge Features for Molecular Property Prediction

GNN / Chemistry Coming Soon

Extends graph attention networks with learnable edge feature transformations for molecular property prediction on the OGB-MolHIV benchmark, achieving competitive performance with existing specialized architectures.

🎮

Entropy-Guided Exploration Bonuses for Sparse-Reward Continuous Control

Reinforcement Learning Coming Soon

Proposes entropy-guided intrinsic reward bonuses to improve exploration efficiency in sparse-reward MuJoCo locomotion environments. Demonstrates improved sample efficiency over baseline algorithms.

🎨

Spectral Normalization Effects on Mode Collapse in Conditional GANs for CIFAR-10

Generative Models Coming Soon

Systematically studies the effect of spectral normalization on mode collapse in conditional GANs trained on CIFAR-10, providing both visual and quantitative analysis (FID, IS) of generation diversity.

🔄

Test-Time Adaptation via Batch Normalization Statistics for Distribution Shift

Domain Adaptation Coming Soon

Explores lightweight test-time adaptation methods that update batch normalization statistics to handle distribution shift on CIFAR-10-C corruption benchmarks, demonstrating practical robustness improvements.

🚀

Papers Coming Soon

We're generating showcase papers across diverse ML subfields. Each paper will include a downloadable PDF, LaTeX source, experiment code, and quality assessment. Check back soon!