·

Open-R1: a fully open reproduction of DeepSeek-R1 - Databubble

Home
Models
News
Compare
Boards
Pricing
About

Latest

Sam Altman reportedly targeted in second attack58m◆The largest orbital compute cluster is open for business3h◆Advantage-Guided Diffusion for Model-Based Reinforcement Learning6h◆FluidFlow: a flow-matching generative model for fluid dynamics surrogates on unstructured meshes6h◆HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?6h◆E3-TIR: Enhanced Experience Exploitation for Tool-Integrated Reasoning6h◆Process Reward Agents for Steering Knowledge-Intensive Reasoning6h◆STIndex: A Context-Aware Multi-Dimensional Spatiotemporal Information Extraction System6h◆Drift and selection in LLM text ecosystems6h◆Joint Interference Detection and Identification via Adversarial Multi-task Learning6h◆Detection of Hate and Threat in Digital Forensics: A Case-Driven Multimodal Approach6h◆MixFlow: Mixed Source Distributions Improve Rectified Flows6h◆MARINER: A 3E-Driven Benchmark for Fine-Grained Perception and Complex Reasoning in Open-Water Environments6h◆SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support6h◆Mapping generative AI use in the human brain: divergent neural, academic, and mental health profiles of functional versus socio emotional AI use6h◆Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation6h◆TiAb Review Plugin: A Browser-Based Tool for AI-Assisted Title and Abstract Screening6h◆LEGO: Latent-space Exploration for Geometry-aware Optimization of Humanoid Kinematic Design6h◆VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learning6h◆3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding6h◆Sam Altman reportedly targeted in second attack58m◆The largest orbital compute cluster is open for business3h◆Advantage-Guided Diffusion for Model-Based Reinforcement Learning6h◆FluidFlow: a flow-matching generative model for fluid dynamics surrogates on unstructured meshes6h◆HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?6h◆E3-TIR: Enhanced Experience Exploitation for Tool-Integrated Reasoning6h◆Process Reward Agents for Steering Knowledge-Intensive Reasoning6h◆STIndex: A Context-Aware Multi-Dimensional Spatiotemporal Information Extraction System6h◆Drift and selection in LLM text ecosystems6h◆Joint Interference Detection and Identification via Adversarial Multi-task Learning6h◆Detection of Hate and Threat in Digital Forensics: A Case-Driven Multimodal Approach6h◆MixFlow: Mixed Source Distributions Improve Rectified Flows6h◆MARINER: A 3E-Driven Benchmark for Fine-Grained Perception and Complex Reasoning in Open-Water Environments6h◆SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support6h◆Mapping generative AI use in the human brain: divergent neural, academic, and mental health profiles of functional versus socio emotional AI use6h◆Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation6h◆TiAb Review Plugin: A Browser-Based Tool for AI-Assisted Title and Abstract Screening6h◆LEGO: Latent-space Exploration for Geometry-aware Optimization of Humanoid Kinematic Design6h◆VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learning6h◆3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding6h◆

News/Open-R1: a fully open reproduction of DeepSeek-R1

huggingfaceJanuary 28, 2025 at 12:00 AM1 min read

Open-R1: a fully open reproduction of DeepSeek-R1

Read original article ↗

No replies yet. Be first.

Source

huggingface

Read original ↗

Related Articles

theverge58m ago

Sam Altman reportedly targeted in second attack

techcrunch3h ago

The largest orbital compute cluster is open for business

Advantage-Guided Diffusion for Model-Based Reinforcement Learning

Home Models News