Aravind Srinivas
VERIFIED TECHNICAL DOSSIERSources checked

Aravind Srinivas

AI Founder

2 Verified ArtifactsSource Checked & Attributed

Verified Proof of Work Artifacts

2 items cataloged

Each artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Aravind Srinivas. Every entry undergoes editorial source verification.

#1
RESEARCH Checked Sep 20, 2026

Bottleneck Transformers for Visual Recognition (BoTNet)

Co-authored BoTNet, an architecture that replaces the final spatial convolutions in ResNet with Multi-Head Self-Attention, achieving 84.7% Top-1 accuracy on ImageNet while substantially improving instance segmentation and object detection on COCO.

Model & Execution Context:ResNet backbone with Multi-Head Self-Attention bottleneck blocks, TPU v3 accelerators, 2D relative position encodings.
Scope & Limitations

Quadratic memory complexity in early spatial layers restricts attention blocks to deeper, downsampled feature maps in the network.

#2
IMPLEMENTATION Checked Sep 20, 2026

Perplexity Sonar and Real-Time Agentic Search Pipeline

Architected Perplexity's conversational search engine and Sonar API, synthesizing real-time multi-source web crawling, dense vector retrieval, dynamic citation parsing, and fine-tuned LLM response generation with strict anti-hallucination attribution.

Model & Execution Context:Llama-3-Sonar fine-tuned checkpoints, TensorRT-LLM, sub-second latency SLA, dynamic search grounding over live web indexes.
Scope & Limitations

Subject to latency variance across heterogeneous external web APIs; adversarial or SEO-manipulated web sources require continuous algorithmic filtering.