LOVE‑R1 Introduces Adaptive Zoom‑In for Long Video Understanding

The new LOVE‑R1 model adds an adaptive zoom‑in mechanism that boosts long video understanding accuracy by ~3.1% over Qwen2.5‑VL on four benchmarks, announced in September 2025. Read more: getnews.me/love-r1-introduces-adapt... #lovr1 #videolanguage #ai

I ll be presenting at the CVPR poster session today in the following workshops:

- What is Next in Multimodal Foundation Models?
- Women in Computer Vision

Feel free to drop by to discuss more about the work! 😃

#CVPR2025 #VideoLanguage #MultimodalAI #WomenInCV #HDVILACaption #HowToCaption #MPI

AdaVid: Adaptive Video-Language Pretraining Contrastive video-language pretraining has demonstrated great success in learning rich and robust video representations. However, deploying such video encoders on compute-constrained edge devices rema...

I'll also be presenting multiple papers at #CVPR2025! First up: "AdaVid: Adaptive Video-Language Pretraining".

🗓️ Thu Jun 12, 12:00-13:00PM
📍 ExHall D Poster #202
🔗 Paper: arxiv.org/abs/2504.12513
🌐 Website: chaitanya100100.github.io/AdaVid/
#VideoLanguage #Pretraining