collaborators

7 papers

cs.AI2026

A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AI

Taye Akinrele, Sindhuja Penchala, Noorbakhsh Amiri Golilarz +2

Cognitive AI seeks to move beyond language generation and autonomous task execution toward systems capable of sustained reasoning, adaptive behavior, persistent memory, and self-re…

cs.CR2026

Cognitive Firewall: A Proactive, Zero-Trust, Multi-Gate Framework for LLM Safety

Michele Guida, Ruslan Shikhhamzayev, Sindhuja Penchala +4

Large language models (LLMs) can be induced to produce harmful content through multi turn strategies in which no single user message appears clearly unsafe. Existing runtime safegu…

cs.CV2026

From Convolution to Transformer: A Comparative Study of U-Net Variants for Brain Tumor and Retinal Vessel Segmentation

Khoa Pham, Sindhuja Penchala, Jiacheng Li +2

Medical image segmentation plays an important role in computer aided diagnosis, treatment planning, and disease monitoring. U-Net has been widely used for biomedical image segmenta…

cs.NE2026

Where to Bind Matters: Hebbian Fast Weights in Vision Transformers for Few-Shot Character Recognition

Gavin Money, Sindhuja Penchala, Jiacheng Li +1

Standard transformer architectures learn fixed slow-weight representations during training and lack mechanisms for rapid adaptation within an episode. In contrast, biological neura…

q-bio.NC2025

Learning in Focus: Detecting Behavioral and Collaborative Engagement Using Vision Transformers

Sindhuja Penchala, Saketh Reddy Kontham, Prachi Bhattacharjee +7

In early childhood education, accurately detecting collaborative and behavioral engagement is essential to foster meaningful learning experiences. This paper presents an AI driven…

cs.CV2025

One Patch is All You Need: Joint Surface Material Reconstruction and Classification from Minimal Visual Cues

Sindhuja Penchala, Gavin Money, Gabriel Marques +5

Understanding material surfaces from sparse visual cues is critical for applications in robotics, simulation, and material perception. However, most existing methods rely on dense…