WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning Paper • 2509.13305 • Published Sep 16 • 90
AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications Paper • 2508.16279 • Published Aug 22 • 53
MediaPipe: A Framework for Building Perception Pipelines Paper • 1906.08172 • Published Jun 14, 2019 • 1
Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Models Paper • 2503.08275 • Published Mar 11 • 4
UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity Paper • 2511.13714 • Published 14 days ago • 10
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B Paper • 2511.06221 • Published 23 days ago • 123
IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System Paper • 2502.05512 • Published Feb 8 • 5
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing Paper • 2509.22186 • Published Sep 26 • 134
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model Paper • 2510.14528 • Published Oct 16 • 98
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Paper • 2511.11793 • Published 17 days ago • 156
PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image Paper • 2511.13648 • Published 14 days ago • 51
Depth Anything 3: Recovering the Visual Space from Any Views Paper • 2511.10647 • Published 18 days ago • 90
view article Article Accelerating Qwen3-8B Agent on Intel® Core™ Ultra with Depth-Pruned Draft Models Sep 29 • 21
Granite 4.0 Collection IBM's new Granite-4.0 models! Run Dynamic GGUFs or fine-tune with Unsloth. • 38 items • Updated Oct 31 • 21