EmbeddingGemma 2: Unified and Efficient Multimodal Representations Paper • 2610.37364 • Published 27 days ago • 39
PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback Paper • 2608.30241 • Published Aug 31 • 13
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities Paper • 2507.06261 • Published Jul 7, 2025 • 71
EmbeddingGemma 2: Unified and Efficient Multimodal Representations Paper • 2610.37364 • Published 27 days ago • 39
EmbeddingGemma 2: Unified and Efficient Multimodal Representations Paper • 2610.37364 • Published 27 days ago • 39
FoundYou: A Unified Model for Personalized Segmentation and Retrieval Paper • 2608.29917 • Published Aug 30
Are Pretrained Image Matchers Good Enough for SAR-Optical Satellite Registration? Paper • 2604.10217 • Published May 1
A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens Paper • 2604.04913 • Published Apr 6 • 10
Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini Paper • 2605.27295 • Published May 26 • 20
TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment Paper • 2604.12012 • Published Apr 13 • 16
MedASR: An Open-Source Model for High-Accuracy Medical Dictation Paper • 2605.16555 • Published May 15
Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini Paper • 2605.27295 • Published May 26 • 20
Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini Paper • 2605.27295 • Published May 26 • 20