Topics
Results for “reinforce”
87 results
- Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning — Hugging Face Papers · Seen · 33 points
- Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent — Hugging Face Papers · Seen · 100 points
- Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents — Hugging Face Papers · Seen · 37 points
- PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training — Hugging Face Papers · Seen · 27 points
- Post-Training NVIDIA Nemotron to Increase Accuracy in Your Scientific Domain — NVIDIA Developer Blog · Seen
- Offline KL-Regularized Reinforcement Learning with Stochastic Transitions — arXiv AI Papers · Seen
- A visual explanation of reinforcement learning — Hacker News · Seen · 166 points
- webAI-Official/TwIL-8B — Hugging Face Models · Seen
- Axion1-0/axion-training-data — Hugging Face Datasets · Seen
- Deploy frontier AI models on AWS Trainium with SGLang-Neuron — AWS Machine Learning Blog · Seen
- StructRL: Model-Free Reinforcement Learning with Replay Graphs — arXiv AI Papers · Seen
- HuggingFaceBio/FineDNA — Hugging Face Datasets · Seen
- Running AV Reasoning Models Within Onboard Compute and Latency Limits — NVIDIA Developer Blog · Seen
- Video-Coder: Reinforcing Agentic Coding for Video Generation — Hugging Face Papers · Seen · 22 points
- Practice Makes Precise: At CoRL, NVIDIA and Partners Reveal How Robots Rehearse Delicate Work in Simulation — NVIDIA Blog · Seen
- Reframe: Observation-Aligned Multi-Teacher On-Policy Distillation for Agentic Visual Reasoning — Hugging Face Papers · Seen · 39 points
- autotrust/Qwen3.8-Flash-Next-E384-FP4-V2 — Hugging Face Models · Seen
- Reinforcement Learning based control of Cancer Chemotherapy treatments — arXiv AI Papers · Seen
- Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training — Hugging Face Papers · Seen · 67 points
- RL-ATTACK: A Generalized Black-Box Adversarial Attack on Language Models via Reinforcement Learning — arXiv AI Papers · Seen
- Dual-Stream LLM-Guided Reward Design for Reject-Inference-Aware Reinforcement Learning in E-Commerce Payment Fraud Detection — arXiv AI Papers · Seen
- Accelerating Reinforcement Learning Weight Refit with the Reshard Collective — NVIDIA Developer Blog · Seen
- EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL — Hugging Face Papers · Seen · 27 points
- NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale — Hugging Face Papers · Seen · 32 points
- EvoMemState: Evolving Memory State for Personal Agents — Hugging Face Papers · Seen · 31 points
- microsoft/Mage-VL-Cowork — Hugging Face Models · Seen
- Regulating Autonomous Mobility-on-Demand Operators with Fixed and Adaptive Penalties: A Multi-Agent Reinforcement Learning Approach — arXiv AI Papers · Seen
- Finite-Time Convergence and Regret Guarantees for Neural Reinforcement Learning in POMDPs — arXiv AI Papers · Seen
- Cooperative Multi-Agent Reinforcement Learning via Epigraph-Form Guided Exploration — arXiv AI Papers · Seen
- Resource-Efficient Reinforcement Learning Post-Training through Elastic Expert Parallelism — arXiv AI Papers · Seen
- On the Opportunities and Challenges of Prefill-to-Autoregressive Cross-Model Transfer — arXiv AI Papers · Seen
- Octopus: One Brain, Many Branches for Latent-KV Multi-Agent Reinforcement Learning — arXiv AI Papers · Seen
- What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents? — Hugging Face Papers · Seen · 35 points
- Axion 1.0: Open Agent Foundation Models, Simplified — Hugging Face Papers · Seen · 48 points
- Augmentation with Reinforcement Transformation for Low-textured Scientific Sketch Image Retrieval — arXiv AI Papers · Seen
- Qwen 3.8 27B on my laptop can interpret model weights, too — Hacker News · Seen · 713 points
- nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB — Hugging Face Models · Seen
- CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents — Hugging Face Papers · Seen · 20 points
- Build, Don't Play: Self-Improving LLM Research Agents Develop a Hearthstone Battlegrounds AI That Rivals Top Players — Hugging Face Papers · Seen · 19 points
- On the Origin and Evolution of Training-Inference Mismatch in LLM Reinforcement Learning — arXiv AI Papers · Seen
- Mage-VL-Cowork: A Full Training Recipe to Learn Hybrid Computer Use From Evolved Harnesses — arXiv AI Papers · Seen
- Li$^{2}$SAO: Lifting Light Singl-Rollout Asynchronous RL Optimization via Group-Relative Actor-Critic Bootstrapping — arXiv AI Papers · Seen
- A tiny world model running games on a Raspberry Pi Pico 2 W — Hacker News · Seen · 270 points
- StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions — Hugging Face Papers · Seen · 80 points
- unsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF — Hugging Face Models · Seen
- Sebastian Raschka's from-scratch video course on building reasoning models — Hacker News · Seen · 849 points
- Jaxnasium: Embracing PyTrees For Any-Agent, Cross-Suite Reinforcement Learning — arXiv AI Papers · Seen
- Curriculum-Driven Deep Reinforcement Learning for Autonomous Far-Range Rocket Landing — arXiv AI Papers · Seen
- ornith-ai/Ornith-1.5-122B — Hugging Face Models · Seen
- Recursive Semantic Divergence for LLM Agent Consistency — arXiv AI Papers · Seen
- pollen-robotics/microduck — GitHub Trending · Seen
- RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution — Hugging Face Papers · Seen · 8 points
- Multi-Turn Reinforcement Learning on Amazon SageMaker AI: A hands-on guide — AWS Machine Learning Blog · Seen
- Using AI Agents to Teach Robots Like Microduck to Walk in Simulation — NVIDIA Developer Blog · Seen
- Hybrid Reasoning Agents: 35–55% fewer tokens and up to 2.6× faster inference — 2 sources · Seen · 44 points
- tencent/Hy-Memory-30B-A3B — Hugging Face Models · Seen
- PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis — Hugging Face Papers · Seen · 72 points
- Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox — Hugging Face Blog · Seen
- Write your own training loop — without managing GPUs — with Amazon SageMaker training session APIs — AWS Machine Learning Blog · Seen
- Announcing new ways to customize models with SageMaker AI, without managing GPUs — AWS Machine Learning Blog · Seen