When Generative Augmentation Hurts: A Benchmark Study of GAN and Diffusion Models for Bias Correction in AI Classification Systems

Generative models are widely used to compensate for class imbalance in AI training pipelines, yet their failure modes under low-data conditions are poorly understood. This paper reports a controlled benchmark comparing three augmentation strategies applied to a fine-grained animal classification task: traditional transforms, FastGAN, and Stable Diffusion 1.5 fine-tuned with Low-Rank Adaptation (LoRA). Using the Oxford-IIIT Pet Dataset with eight artificially underrepresented breeds, we find that FastGAN augmentation does not merely underperform at very low training set sizes but actively increases classifier bias, with a statistically significant large effect across three random seeds (bias gap increase: +20.7%, Cohen's d = +5.03, p = 0.013). The effect size here is large enough to give confidence in the direction of the finding despite the small number of seeds. Feature embedding analysis using t-distributed Stochastic Neighbor Embedding reveals that FastGAN images for severe-minority breeds form tight isolated clusters outside the real image distribution, a pattern consistent with mode collapse. Stable Diffusion with Low-Rank Adaptation produced the best results overall, achieving the highest macro F1 (0.9125 plus or minus 0.0047) and a 13.1% reduction in the bias gap relative to the unaugmented baseline. The data suggest a sample-size boundary somewhere between 20 and 50 training images per class below which GAN augmentation becomes harmful in this setting, though further work across additional domains is needed to establish where that boundary sits more precisely. All experiments run on a consumer-grade GPU with 6 to 8 GB of memory, with no cloud compute required.

Advances in Transformers for Robotic Applications: A Review

The introduction of Transformers architecture has brought about significant breakthroughs in Deep Learning (DL), particularly within Natural Language Processing (NLP). Since their inception, Transformers have outperformed many traditional neural network architectures due to their "self-attention" mechanism and their scalability across various applications. In this paper, we cover the use of Transformers in Robotics. We go through recent advances and trends in Transformer architectures and examine their integration into robotic perception, planning, and control for autonomous systems. Furthermore, we review past work and recent research on use of Transformers in Robotics as pre-trained foundation models and integration of Transformers with Deep Reinforcement Learning (DRL) for autonomous systems. We discuss how different Transformer variants are being adapted in robotics for reliable planning and perception, increasing human-robot interaction, long-horizon decision-making, and generalization. Finally, we address limitations and challenges, offering insight and suggestions for future research directions.

Enhancing Trust in LLMs: Algorithms for Comparing and Interpreting LLMs

This paper surveys evaluation techniques to enhance the trustworthiness and understanding of Large Language Models (LLMs). As reliance on LLMs grows, ensuring their reliability, fairness, and transparency is crucial. We explore algorithmic methods and metrics to assess LLM performance, identify weaknesses, and guide development towards more trustworthy applications. Key evaluation metrics include Perplexity Measurement, NLP metrics (BLEU, ROUGE, METEOR, BERTScore, GLEU, Word Error Rate, Character Error Rate), Zero-Shot and Few-Shot Learning Performance, Transfer Learning Evaluation, Adversarial Testing, and Fairness and Bias Evaluation. We introduce innovative approaches like LLMMaps for stratified evaluation, Benchmarking and Leaderboards for competitive assessment, Stratified Analysis for in-depth understanding, Visualization of Blooms Taxonomy for cognitive level accuracy distribution, Hallucination Score for quantifying inaccuracies, Knowledge Stratification Strategy for hierarchical analysis, and Machine Learning Models for Hierarchy Generation. Human Evaluation is highlighted for capturing nuances that automated metrics may miss. These techniques form a framework for evaluating LLMs, aiming to enhance transparency, guide development, and establish user trust. Future papers will describe metric visualization and demonstrate each approach on practical examples.

The Cognitive Type Project -- Mapping Typography to Cognition

The Cognitive Type Project is focused on developing computational tools to enable the design of typefaces with varying cognitive properties. This initiative aims to empower typographers to craft fonts that enhance click-through rates for online ads, improve reading levels in children's books, enable dyslexics to create personalized type, or provide insights into customer reactions to textual content in media. A significant challenge in research related to mapping typography to cognition is the creation of thousands of typefaces with minor variations, a process that is both labor-intensive and requires the expertise of skilled typographers. Cognitive science research highlights that the design and form of letters, along with the text's overall layout, are crucial in determining the ease of reading and other cognitive properties of type such as perceived beauty and memorability. These factors affect not only the legibility and clarity of information presentation but also the likability of a typeface.

DC-Art-GAN: Stable Procedural Content Generation using DC-GANs for Digital Art

Art is an artistic method of using digital technologies as a part of the generative or creative process. With the advent of digital currency and NFTs (Non-Fungible Token), the demand for digital art is growing aggressively. In this manuscript, we advocate the concept of using deep generative networks with adversarial training for a stable and variant art generation. The work mainly focuses on using the Deep Convolutional Generative Adversarial Network (DC-GAN) and explores the techniques to address the common pitfalls in GAN training. We compare various architectures and designs of DC-GANs to arrive at a recommendable design choice for a stable and realistic generation. The main focus of the work is to generate realistic images that do not exist in reality but are synthesised from random noise by the proposed model. We provide visual results of generated animal face images (some pieces of evidence showing a blend of species) along with recommendations for training, architecture and design choices. We also show how training image preprocessing plays a massive role in GAN training.