olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models

1 code implementation • 25 Feb 2025 • Jake Poznanski, Jon Borchardt, Jason Dunkelberger, Regan Huff, Daniel Lin, Aman Rangapur, Christopher Wilhelm, Kyle Lo, Luca Soldaini

PDF documents have the potential to provide trillions of novel, high-quality tokens for training language models.

Diversity Language Modeling +1

2 OLMo 2 Furious

2 code implementations • 31 Dec 2024 • Team OLMo, Pete Walsh, Luca Soldaini, Dirk Groeneveld, Kyle Lo, Shane Arora, Akshita Bhagia, Yuling Gu, Shengyi Huang, Matt Jordan, Nathan Lambert, Dustin Schwenk, Oyvind Tafjord, Taira Anderson, David Atkinson, Faeze Brahman, Christopher Clark, Pradeep Dasigi, Nouha Dziri, Michal Guerquin, Hamish Ivison, Pang Wei Koh, Jiacheng Liu, Saumya Malik, William Merrill, Lester James V. Miranda, Jacob Morrison, Tyler Murray, Crystal Nam, Valentina Pyatkin, Aman Rangapur, Michael Schmitz, Sam Skjonsberg, David Wadden, Christopher Wilhelm, Michael Wilson, Luke Zettlemoyer, Ali Farhadi, Noah A. Smith, Hannaneh Hajishirzi

Our modified model architecture and training recipe achieve both better training stability and improved per-token efficiency.

Piecing It All Together: Verifying Multi-Hop Multimodal Claims

no code implementations • 14 Nov 2024 • Haoran Wang, Aman Rangapur, Xiongxiao Xu, Yueqing Liang, Haroon Gharwi, Carl Yang, Kai Shu

Existing claim verification datasets often do not require systems to perform complex reasoning or effectively interpret multimodal evidence.

16k All +1

The Battle of LLMs: A Comparative Study in Conversational QA Tasks

no code implementations • 28 May 2024 • Aryan Rangapur, Aman Rangapur

This research delves into the responses generated by ChatGPT, GPT-4, Gemini, Mixtral and Claude across different Conversational QA corpora.

Fin-Fact: A Benchmark Dataset for Multimodal Financial Fact Checking and Explanation Generation

1 code implementation • 15 Sep 2023 • Aman Rangapur, Haoran Wang, Ling Jian, Kai Shu

Fact-checking in financial domain is under explored, and there is a shortage of quality dataset in this domain.

Explanation Generation Fact Checking +1

Investigating Online Financial Misinformation and Its Consequences: A Computational Perspective

no code implementations • 6 Sep 2023 • Aman Rangapur, Haoran Wang, Kai Shu

In conclusion, this research paper sheds light on the pervasive issue of online financial misinformation and its wide-ranging consequences.

Misinformation

ChatGPT-Crawler: Find out if ChatGPT really knows what it's talking about

no code implementations • 6 Apr 2023 • Aman Rangapur, Haoran Wang

Large language models have gained considerable interest for their impressive performance on various tasks.

Natural Language Inference

DDoSDet: An approach to Detect DDoS attacks using Neural Networks

no code implementations • 24 Jan 2022 • Aman Rangapur, Tarun Kanakam, Ajith Jubilson

Cyber-attacks have been one of the deadliest attacks in today's world.

EfficientWord-Net: An Open Source Hotword Detection Engine based on One-shot Learning

1 code implementation • 31 Oct 2021 • Chidhambararajan R, Aman Rangapur, Sibi Chakkaravarthy Sethuraman

Voice assistants like Siri, Google Assistant, Alexa etc.

One-Shot Learning

Phish-Defence: Phishing Detection Using Deep Recurrent Neural Networks

no code implementations • 26 Oct 2021 • Aman Rangapur, Tarun Kanakam, Dhanvanthini P

In the growing world of the internet, the number of ways to obtain crucial data such as passwords and login credentials, as well as sensitive personal information has expanded.