Tagged: multimodal-models

9 articles

Latest

LayoutLM hits 95% accuracy on document AI benchmarks, leaving OCR-only approaches behind

LAION's 10M-hour video dataset trains models that beat InternVid by 2.1 points

Kakao Brain open-sources Google's ALIGN and ViT, trained on 700M public image-text pairs

Alibaba's Qwen3.8-27B beats bigger Qwen3.7-Plus on coding, ships Apache 2.0

MiniMax's H3 is the first open-source model to top an AI video ranking

CLIP drops the training wheels: Zero-shot vision matches ResNet-50

GPT-4 Passes the Bar, But the Real Story Is Predictability

OpenAI's o3 and o4-mini can now 'think' with images, not just see them

UCLA's ConTextual benchmark: 506 text-rich tasks where GPT-4V beats humans once