Sindhuja Penchala

Gavin Money, Sindhuja Penchala, Jiacheng Li et al.

Standard transformer architectures learn fixed slow-weight representations during training and lack mechanisms for rapid adaptation within an episode. In contrast, biological neural systems address this through fast synaptic updates that form transient associative memories during inference, a property known as Hebbian plasticity. In this paper, we conduct an empirical study of Hebbian Fast-Weight (HFW) modules integrated into multiple transformer backbones, including ViT-Small, DeiT-Small, and Swin-Tiny. We evaluate six model variants: ViT, DeiT, Swin, ViT-Hebbian, DeiT-Hebbian, and Swin-Hebbian on 5-way 1-shot and 5-way 5-shot classification tasks using the Omniglot benchmark under a Prototypical Network meta-learning framework. We propose a single module placement strategy for Swin-Tiny in which one HFW module is applied to the final stage feature map after all hierarchical stages have completed. This design avoids the training instability caused by placing separate Hebbian modules at each stage and achieves the highest test accuracy across all six models (96.2\% at 1-shot; 99.2\% at 5-shot), outperforming its non-Hebbian baseline by $+0.3$ percentage points at 1-shot. We analyze the interaction between Swin's shifted window inductive bias and episode-level Hebbian binding, discuss why per-block placement fails for ViT and DeiT variants in a low-data regime, and situate the results within the wider literature on fast and slow-weight meta-learning.

Noorbakhsh Amiri Golilarz, Sindhuja Penchala, Shahram Rahimi

Artificial intelligence has advanced rapidly across perception, language, reasoning, and multimodal domains. Yet despite these achievements, modern AI systems remain fundamentally limited in their ability to self-monitor, self-correct, and regulate their behavior autonomously in dynamic contexts. This paper identifies and analyzes seven core deficiencies that constrain contemporary AI models: the absence of intrinsic self-monitoring, lack of meta-cognitive awareness, fixed and non-adaptive learning mechanisms, inability to restructure goals, lack of representational maintenance, insufficient embodied feedback, and the absence of intrinsic agency. Alongside identifying these limitations, we also outline a forward-looking perspective on how AI may evolve beyond them through architectures that mirror neurocognitive principles. We argue that these structural limitations prevent current architectures, including deep learning and transformer-based systems, from achieving robust generalization, lifelong adaptability, and real-world autonomy. Drawing on a comparative analysis of artificial systems and biological cognition [7], and integrating insights from AI research, cognitive science, and neuroscience, we outline how these capabilities are absent in current models and why scaling alone cannot resolve them. We conclude by advocating for a paradigmatic shift toward cognitively grounded AI (cognitive autonomy) capable of self-directed adaptation, dynamic representation management, and intentional, goal-oriented behavior, paired with reformative oversight mechanisms [8] that ensure autonomous systems remain interpretable, governable, and aligned with human values.

Sindhuja Penchala, Gavin Money, Gabriel Marques et al.

Understanding material surfaces from sparse visual cues is critical for applications in robotics, simulation, and material perception. However, most existing methods rely on dense or full-scene observations, limiting their effectiveness in constrained or partial view environment. To address this challenge, we introduce SMARC, a unified model for Surface MAterial Reconstruction and Classification from minimal visual input. By giving only a single 10% contiguous patch of the image, SMARC recognizes and reconstructs the full RGB surface while simultaneously classifying the material category. Our architecture combines a Partial Convolutional U-Net with a classification head, enabling both spatial inpainting and semantic understanding under extreme observation sparsity. We compared SMARC against five models including convolutional autoencoders [17], Vision Transformer (ViT) [13], Masked Autoencoder (MAE) [5], Swin Transformer [9], and DETR [2] using Touch and Go dataset [16] of real-world surface textures. SMARC achieves state-of-the-art results with a PSNR of 17.55 dB and a material classification accuracy of 85.10%. Our findings highlight the advantages of partial convolution in spatial reasoning under missing data and establish a strong foundation for minimal-vision surface understanding.

Sindhuja Penchala, Saketh Reddy Kontham, Prachi Bhattacharjee et al.

In early childhood education, accurately detecting behavioral and collaborative engagement is essential for fostering meaningful learning experiences. This paper presents an AI-driven approach that leverages Vision Transformers (ViTs) to automatically classify children's engagement using visual cues such as gaze direction, interaction, and peer collaboration. Utilizing the Child-Play gaze dataset, our method is trained on annotated video segments to classify behavioral and collaborative engagement states (e.g., engaged, not engaged, collaborative, not collaborative). We evaluated three state-of-the-art transformer models: Vision Transformer (ViT), Data-efficient Image Transformer (DeiT), and Swin Transformer. Among these, the Swin Transformer achieved the highest classification performance with an accuracy of 97.58%, demonstrating its effectiveness in modeling local and global attention. Our results highlight the potential of transformer-based architectures for scalable, automated engagement analysis in real-world educational settings.