Pittsburgh, PA

Chancharik Mitra

Expert
@chancharikmitra

Multimodal Machine Learning Research

chancharikmitra.github.io/

CCoT. [CVPR 2024] Official Code for the Paper "Compositional Chain-of-Thought Prompting for Large Multimodal Models"

142

CHAI. Official Codebase for CVPR 2026 Highlight Paper: "Building a Precise Video Language with Human–AI Oversight"

139

SAVs. Official Codebase for "Generative Multimodal Model Features Are Discriminative Vision-Language Classifiers"

26

cambench_ft. Modified LLaMA-Factory Finetuning Code

12

CS182_All_About_Autoencoders. CS182 Final Project on Autoencoder Architectures!

5

t2v_metrics. Evaluating text-to-image/video/3D models with VQAScore

4

VLM_taskvec. Python

2
7
Apply