Ritvik Pandey

@ritvikpandey21

co-founder @pulse__ai

San Francisco, CA

Joined December 2018

Replies Reposts Media

Pinned
Ritvik Pandey
@ritvikpandey21
Feb 6, 2025
Document ingestion & Gemini 2.0 caused a lot of buzz this week. As builders in this space, here's our take: Data ingestion is a multistep pipeline, and maintaining confidence from LLM nondeterministic outputs over millions of pages is a problem. (1/7)
16
Ritvik Pandey
@ritvikpandey21
Sep 11
A few months ago, the team at @Pulse__AI launched PulseBench-Tab, our frontier table extraction benchmark with 1,820 human-annotated tables across 9 languages. Our evals team has updated the benchmark against the latest generation of document parsers and frontier models. Pulse
5
Ritvik Pandey
@ritvikpandey21
Sep 10
The more production ai systems we build the more convinced i am that most of our “model problems” will eventually become systems problems
Ritvik Pandey
@ritvikpandey21
Sep 4
We're continuously training our models and have a few exciting updates rolling out in the next couple weeks ;) Let's not forget to include @Pulse__AI , we have a great performance to price ratio
Jerry Liu
@jerryjliu0
Sep 4
We've massively improved our document parsing capabilities across the board in the past ~3 months. Our LlamaParse cost-effective mode is one of the cheapest OCR solutions out there at <0.4c per page, and it has improved a lot on parsing since when we first put out the
Ritvik Pandey
@ritvikpandey21
Sep 4
. @reductoai released their latest model this week, r-1. The @Pulse__AI team ran it on PulseBench-Tab, our frontier table-extraction benchmark consisting of thousands of human-annotated, multilingual tables across 9 languages. Pulse Ultra 2 remains state-of-the-art with r-1
Adit
@aditabrm
Sep 1
01:22
Today we’re announcing r-1, our new document parsing model. It’s more accurate than our most powerful agentic OCR models, faster, and up to 6x cheaper. At @reductoai, we spent two years building specialized models for complex visual layouts, tables spanning multiple pages, and
6