OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks Paper • 2604.08539 • Published 6 days ago • 46
ClawBench: Can AI Agents Complete Everyday Online Tasks? Paper • 2604.08523 • Published 6 days ago • 251
MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping Paper • 2604.08364 • Published 6 days ago • 94
Automating Database-Native Function Code Synthesis with LLMs Paper • 2604.06231 • Published 13 days ago • 16
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published 7 days ago • 308
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver Paper • 2604.08377 • Published 6 days ago • 272
Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning Paper • 2604.04746 • Published 7 days ago • 68
GPT-1900 Collection Pre-1900 LLMs for physics reasoning. RL models are physics-only; use the SFT model for general chat. Tune temperature (0.6-0.7). • 11 items • Updated 12 days ago • 6
MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome Paper • 2603.28407 • Published 15 days ago • 68
ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers Paper • 2603.24414 • Published 20 days ago • 183
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels Paper • 2603.19312 • Published Mar 13 • 26
LeWM Collection Official checkpoints and datasets related to LeWM paper. • 9 items • Updated 18 days ago • 23
Anime & Art Collection Collection of datasets featuring anime, art, and creative visual content. Includes images, videos, and metadata for ML tasks. • 54 items • Updated Mar 2 • 6