RAG BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms Paper • 2607.26497 • Published 15 days ago • 50
BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms Paper • 2607.26497 • Published 15 days ago • 50
Embodied AI TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM Paper • 2607.27205 • Published 16 days ago • 139 GST-Bench: Can VLMs Develop Global Spatial Awareness from Video? Paper • 2608.05747 • Published 8 days ago • 46
TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM Paper • 2607.27205 • Published 16 days ago • 139
GST-Bench: Can VLMs Develop Global Spatial Awareness from Video? Paper • 2608.05747 • Published 8 days ago • 46
Memory Engineering Metis: Memory Foundation Model Paper • 2607.26760 • Published 16 days ago • 270 Efficient Memory Management for Large Language Model Serving with PagedAttention Paper • 2309.06180 • Published Sep 12, 2023 • 66
Efficient Memory Management for Large Language Model Serving with PagedAttention Paper • 2309.06180 • Published Sep 12, 2023 • 66
RAG BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms Paper • 2607.26497 • Published 15 days ago • 50
BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms Paper • 2607.26497 • Published 15 days ago • 50
Memory Engineering Metis: Memory Foundation Model Paper • 2607.26760 • Published 16 days ago • 270 Efficient Memory Management for Large Language Model Serving with PagedAttention Paper • 2309.06180 • Published Sep 12, 2023 • 66
Efficient Memory Management for Large Language Model Serving with PagedAttention Paper • 2309.06180 • Published Sep 12, 2023 • 66
Embodied AI TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM Paper • 2607.27205 • Published 16 days ago • 139 GST-Bench: Can VLMs Develop Global Spatial Awareness from Video? Paper • 2608.05747 • Published 8 days ago • 46
TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM Paper • 2607.27205 • Published 16 days ago • 139
GST-Bench: Can VLMs Develop Global Spatial Awareness from Video? Paper • 2608.05747 • Published 8 days ago • 46
