Intelligence per Watt: Measuring Intelligence Efficiency of Local AI Paper β’ 2511.07885 β’ Published Nov 11 β’ 7
Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds Paper β’ 2511.08892 β’ Published Nov 12 β’ 201
Running on Zero Featured 111 VLM Object Understanding π¦ 111 Explore object detection, visual grounding, keypoint Detecti
view post Post 1979 New drop! π₯ The VLM Object Understanding Comparison Space now runs with Qwen3-VL-4B and moondream3.You can compare how models reason about images π§ Bonus: thanks to @ariG23498 , you now get auto-suggested prompts to explore faster.Letβs gooo sergiopaniego/vlm_object_understanding See translation π₯ 5 5 + Reply
Less is More: Recursive Reasoning with Tiny Networks Paper β’ 2510.04871 β’ Published Oct 6 β’ 500
SmolVLM: Redefining small and efficient multimodal models Paper β’ 2504.05299 β’ Published Apr 7 β’ 202
A Survey of Context Engineering for Large Language Models Paper β’ 2507.13334 β’ Published Jul 17 β’ 259
Running on Zero MCP Featured 2.63k Wan2.2 14B Fast π₯ 2.63k generate a video from an image with a text prompt
table-detection-ocr-htr Collection Demos of integrated applications which can detect tables and perform OCR/HTR β’ 3 items β’ Updated Feb 21
Prithvi WxC: Foundation Model for Weather and Climate Paper β’ 2409.13598 β’ Published Sep 20, 2024 β’ 45