Multimodal - a mpolak Collection

mpolak 's Collections

Multimodal

updated Jul 22

MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?

Paper • 2407.04842 • Published Jul 5 • 52

Note Base for discussion about NSFW and Biases in AI
MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation

Paper • 2407.00468 • Published Jun 29 • 34

Note Critique on why some benchmarks are biased when comparing LLM and MLLM. New benchmark fixing those errors
Qwen2 Technical Report

Paper • 2407.10671 • Published Jul 15 • 160

Note New SOTA - better than llama!