ClawArena: Benchmarking AI Agents in Evolving Information Environments Paper • 2604.04202 • Published 12 days ago • 36
Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw Paper • 2604.04759 • Published 11 days ago • 22
Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory Paper • 2604.01007 • Published 15 days ago • 31
Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation Paper • 2603.12793 • Published Mar 13 • 38
MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild Paper • 2603.17187 • Published 30 days ago • 138
Mistral Small 4 Collection A state-of-the-art model, open-weight, with a granular Mixture-of-Experts architecture that fuses instruct, reasoning and agentic skills. • 3 items • Updated about 1 month ago • 66
Nemotron-Post-Training-v3 Collection Collection of datasets used in the post-training phase of Nemotron Nano and Super v3. • 28 items • Updated 1 day ago • 123
MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe Paper • 2509.18154 • Published Sep 16, 2025 • 56
view article Article GGML and llama.cpp join HF to ensure the long-term progress of Local AI +4 Feb 20 • 503
MAI-UI Technical Report: Real-World Centric Foundation GUI Agents Paper • 2512.22047 • Published Dec 26, 2025 • 30
OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation Paper • 2601.15369 • Published Jan 21 • 21
Towards Scalable Pre-training of Visual Tokenizers for Generation Paper • 2512.13687 • Published Dec 15, 2025 • 106