Topics
Results for “reinforcement learning”
23 results
- Hybrid Reasoning Agents: 35–55% fewer tokens and up to 2.6× faster inference — 2 sources · Seen · 506 points
- tencent/Hy-Memory-30B-A3B — Hugging Face Models · Seen
- convaiinnovations/laya — Hugging Face Models · Seen
- OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools — Hugging Face Papers · Seen · 41 points
- StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions — Hugging Face Papers · Seen · 20 points
- Player-1: Learning to Play from Synthetic Experience — Hugging Face Papers · Seen · 344 points
- PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training — Hugging Face Papers · Seen · 26 points
- miniTE: Diagnosing and Bridging the Execution Gap in Native NVFP4 Reinforcement Learning — arXiv AI Papers · Seen
- Web Agent Agentic Reinforcement Learning Decision Model Under Multi-Cost and Failure Risk — arXiv AI Papers · Seen
- Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes — Hugging Face Papers · Seen · 134 points
- ECHOES: Seeing Beyond the Current Image via Recursive History Compression and Privileged On-Policy Distillation — arXiv AI Papers · Seen
- MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe — Hugging Face Papers · Seen · 63 points
- More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning — Hugging Face Papers · Seen · 82 points
- Mosaic: Multi-Session Agentic Reinforcement Learning — Hugging Face Papers · Seen · 54 points
- DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models — Hugging Face Papers · Seen · 319 points
- AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards — Hugging Face Papers · Seen · 118 points
- JetBrains/Mellum2.1-12B-A2.5B-Thinking — Hugging Face Models · Seen
- GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning — arXiv AI Papers · Seen
- RLPE: Teaching LLMs to Prompt with Reinforcement Learning — arXiv AI Papers · Seen
- A Geometric Perspective on Reward Function Updates in Inverse Reinforcement Learning — arXiv AI Papers · Seen
- VH-GPO: Verified Handoff for LLM Agent Reinforcement Learning — arXiv AI Papers · Seen
- GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games — arXiv AI Papers · Seen
- AlphaNIST — Hacker News · Seen · 78 points