Image and Video Segmentation with SAM 2, Gemma 2 for Efficient Language Models, Boosting Small Models with Contrastive Fine-Tuning, and MM-Vet v2 Challenges Large Multimodal Models

AI Papers Podcast

SAM 2: Segment Anything in Images and Videos Gemma 2: Improving Open Language Models at a Practical Size Coarse Correspondence Elicit 3D Spacetime Understanding in Multimodal Language Model Improving Text Embeddings for Smaller Language Models Using Contrastive Fine-tuning OmniParser for Pure Vision Based GUI Agent SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities