view article Article Introducing smolagents: simple agents that write actions in code. +1 m-ric, merve, thomwolf • Dec 31, 2024 • 1.2k
view article Article DABStep: Data Agent Benchmark for Multi-step Reasoning +5 eggie5, martinigoyanes, frisokingma, andreumora, lvwerra, thomwolf, m-ric • Feb 4, 2025 • 131
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels Paper • 2603.19312 • Published Mar 13 • 50
view article Article Welcome Gemma 4: Frontier multimodal intelligence on device +5 merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift • Apr 2 • 910
Running on CPU Upgrade Featured 3.22k The Smol Training Playbook 📚 3.22k The secrets to building world-class LLMs
DINOv3 Collection DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 15 items • Updated Mar 10 • 674
view article Article Gemma 3n fully available in the open-source ecosystem! +6 ariG23498, pcuenq, sergiopaniego, reach-vb, FL33TW00D-HF, Xenova, Steveeeeeeen, kashif • Jun 26, 2025 • 121
Runtime error Agents 38 V-JEPA 2 - Streaming Video Classification 🌍 38 Run V-JEPA 2 on a video stream for Video Classification
SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics Paper • 2506.01844 • Published Jun 2, 2025 • 161
view article Article SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data +7 danaaubakirova, andito, merve, ariG23498, fracapuano, loubnabnl, pcuenq, mshukor, cadene • Jun 3, 2025 • 356
Running 3.9k The Ultra-Scale Playbook 🌌 3.9k The ultimate guide to training LLM on large GPU Clusters