Mistral Medium 3.5 Collection Our first flaship models handling instruction-following, reasoning, and coding in a single set of opened-weights. • 2 items • Updated Apr 29 • 18
AutoMedBench: Towards Medical AutoResearch with Agentic AI Models Paper • 2606.01961 • Published 7 days ago • 25
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration Paper • 2605.20025 • Published 20 days ago • 186
Ling 2.6 Collection Ling-2.6 series is designed for real-world agents that require fast responses, strong execution, and high token efficiency, with several sized SKUs. • 4 items • Updated 5 days ago • 13
view article Article NEO-unify: Building Native Multimodal Unified Models End to End sensenova • Mar 5 • 164
VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation Paper • 2604.21375 • Published Apr 23 • 19
ClawArena: Benchmarking AI Agents in Evolving Information Environments Paper • 2604.04202 • Published Apr 5 • 37
Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw Paper • 2604.04759 • Published Apr 6 • 24
Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory Paper • 2604.01007 • Published Apr 2 • 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 Mar 17 • 140
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 Mar 16 • 74
Nemotron-Post-Training-v3 Collection Collection of datasets used in the post-training phase of Nemotron Nano, Super, and Ultra v3. • 52 items • Updated about 5 hours ago • 151
MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe Paper • 2509.18154 • Published Sep 16, 2025 • 62