-
stanford-oval/churro-3B
Image-Text-to-Text • 4B • Updated • 607 • 2 -
stanford-oval/churro-dataset
Viewer • Updated • 99.5k • 589 • 2 -
CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition
Paper • 2509.19768 • Published • 2
AI & ML interests
We build LLM-Augmented Cognition Systems (LLM-CSys) that combine the expressive language skills of LLMs with the interpretability and reliability of software systems. We connect LLMs with databases, compilers, and executive functions to create assistants that are more trustworthy and helpful.
Recent Activity
Papers

Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language Models

CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition
We build LLM-Augmented Cognition Systems (LLM-CSys) that combine the expressive language skills of LLMs with the interpretability and reliability of software systems. We connect LLMs with databases, compilers, and executive functions to create assistants that are more trustworthy and helpful.
-
stanford-oval/Llama-2-7b-WikiChat
Text Generation • 7B • Updated • 318 • 26 -
stanford-oval/Llama-2-7b-WikiChat-fused
Text Generation • 7B • Updated • 309 • 6 -
stanford-oval/wikipedia_colbert_index
Updated • 66 • 4 -
WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia
Paper • 2305.14292 • Published
-
stanford-oval/churro-3B
Image-Text-to-Text • 4B • Updated • 607 • 2 -
stanford-oval/churro-dataset
Viewer • Updated • 99.5k • 589 • 2 -
CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition
Paper • 2509.19768 • Published • 2
-
stanford-oval/Llama-2-7b-WikiChat
Text Generation • 7B • Updated • 318 • 26 -
stanford-oval/Llama-2-7b-WikiChat-fused
Text Generation • 7B • Updated • 309 • 6 -
stanford-oval/wikipedia_colbert_index
Updated • 66 • 4 -
WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia
Paper • 2305.14292 • Published
models
8

stanford-oval/eynollah_binarizer_onnx

stanford-oval/churro-3B

stanford-oval/Llama-2-7b-WikiChat-fused

stanford-oval/Llama-2-7b-WikiChat

stanford-oval/bge-m3-zeroshot-v2.0-onnx-o4

stanford-oval/llama-7b-wikiwebquestions

stanford-oval/llama-7b-wikiwebquestions-qald7
