5 papers
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…
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…