10 papers
Approve What, Exactly? Effect Binding and Trusted Rendering for Agent Step-Up Authorization
Sai Varun Kodathala, Prashanth Pollishetty, Jaylen Cargill
AI agents now pause for approval before they send money, delete files or email outsiders, and that approval is usually treated as a second factor. We argue it is one only when comp…
Prompt, Probe, Train, or Annotate? Single-camera sports video understanding in amateur settings
Sai Varun Kodathala, Prashanth Pollishetty, Jaylen Cargill
Video understanding is usually benchmarked on curated, single-actor, or professionally filmed clips, and a strong score there is routinely read as evidence a model is robust enough…
aiAuthZ: Off-Host, Identity-Bound Authorization for AI Agents
Sai Varun Kodathala
AI agents issue tool calls on the basis of text they cannot verify, so any party who controls part of the context can forge the appearance of authority. I evaluate 15 contemporary…
LLMs can Compress LLMs: Adaptive Pruning by Agents
Sai Varun Kodathala, Rakesh Vunnam
As Large Language Models (LLMs) continue to scale, post-training pruning has emerged as a promising approach to reduce computational costs while preserving performance. Existing me…
Can Large Language Models Solve Engineering Equations? A Systematic Comparison of Direct Prediction and Solver-Assisted Approaches
Sai Varun Kodathala, Rakesh Vunnam
Transcendental equations requiring iterative numerical solution pervade engineering practice, from fluid mechanics friction factor calculations to orbital position determination. W…
Temporal vs. Spatial: Comparing DINOv3 and V-JEPA2 Feature Representations for Video Action Analysis
Sai Varun Kodathala, Rakesh Vunnam
This study presents a comprehensive comparative analysis of two prominent self-supervised learning architectures for video action recognition: DINOv3, which processes frames indepe…
Six Sigma For Neural Networks: Taguchi-based optimization
Sai Varun Kodathala
The optimization of hyperparameters in convolutional neural networks (CNNs) remains a challenging and computationally expensive process, often requiring extensive trial-and-error a…
Fast OTSU Thresholding Using Bisection Method
Sai Varun Kodathala
The Otsu thresholding algorithm represents a fundamental technique in image segmentation, yet its computational efficiency is severely limited by exhaustive search requirements acr…
The Describe-Then-Generate Bottleneck: How VLM Descriptions Alter Image Generation Outcomes
Sai Varun Kodathala, Rakesh Vunnam
With the increasing integration of multimodal AI systems in creative workflows, understanding information loss in vision-language-vision pipelines has become important for evaluati…
SV3.3B: A Sports Video Understanding Model for Action Recognition
Sai Varun Kodathala, Yashwanth Reddy Vutukoori, Rakesh Vunnam
This paper addresses the challenge of automated sports video analysis, which has traditionally been limited by computationally intensive models requiring server-side processing and…