Mantis
Official code for Paper "Mantis: Multi-Image Instruction Tuning" [TMLR 2024 Best Paper]
- 243
- Python
- Apache-2.0
- 11 mo ago
Official code for Paper "Mantis: Multi-Image Instruction Tuning" [TMLR 2024 Best Paper]
🔥 [ICLR 2025] Official Benchmark Toolkits for "Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmark"
A Gradio-based demonstration for the AllenAI Molmo2-8B multimodal model, enabling image QA, multi-image pointing, video QA, and temporal tracking. Users upload images or videos, provide natural language prompts.