Unified Multi-Image Composition with Sequence Modeling
Skywork
company
Verified
AI & ML interests
None defined yet.
Recent Activity
Papers
Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch
Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation
A Unified DiT Multimodal Model for Image Generation, Editing, and Understanding
Unified Autoregressive Modeling for Visual Understanding and Generation
Scaling preference data curation to the extreme
-
Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy
Paper • 2507.01352 • Published • 56 -
Skywork/Skywork-Reward-V2-Llama-3.1-8B
Text Classification • 8B • Updated • 55.8k • 35 -
Skywork/Skywork-Reward-V2-Llama-3.1-8B-40M
Text Classification • 8B • Updated • 2.75k • 20 -
Skywork/Skywork-Reward-V2-Llama-3.2-1B
Text Classification • 1B • Updated • 8.68k • 6
Multimodal Hybrid Reinforcement Learning for Reasoning
-
Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning
Paper • 2504.16656 • Published • 57 -
Skywork/Skywork-R1V2-38B
Image-Text-to-Text • 38B • Updated • 49 • 126 -
Skywork/Skywork-R1V2-38B-AWQ
Image-Text-to-Text • Updated • 59 • 11 -
Skywork/Skywork-VL-Reward-7B
Image-Text-to-Text • 8B • Updated • 429 • 47
A Chinese Multimodal Benchmark for Evaluating STEM Reasoning Capabilities of VLMs
SkyReels V1 open models collections
Skywork reward model series
-
Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs
Paper • 2410.18451 • Published • 20 -
Skywork/Skywork-Reward-Gemma-2-27B-v0.2
Text Classification • 27B • Updated • 791 • 33 -
Skywork/Skywork-Reward-Llama-3.1-8B-v0.2
Text Classification • 8B • Updated • 21.7k • 39 -
Skywork/Skywork-Reward-Gemma-2-27B
Text Classification • 27B • Updated • 80 • 48
Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch
-
Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch
Paper • 2512.02395 • Published • 47 -
Skywork/R1V4
Image-Text-to-Text • Updated • 13 -
Skywork/Skywork-VL-Reward-7B
Image-Text-to-Text • 8B • Updated • 429 • 47 -
Mungert/Skywork-VL-Reward-7B-GGUF
Image-Text-to-Text • 8B • Updated • 236
MindLink demonstrates strong performance across various common benchmarks and is widely applicable in diverse AI scenarios.
Advanced multimodal reasoning model
-
Skywork-R1V3 Technical Report
Paper • 2507.06167 • Published • 73 -
Skywork/Skywork-R1V3-38B
Image-Text-to-Text • 38B • Updated • 114 • 88 -
bartowski/Skywork_Skywork-R1V3-38B-GGUF
Image-Text-to-Text • 33B • Updated • 6.35k • 6 -
brandonbeiler/Skywork-R1V3-38B-FP8-Dynamic
Image-Text-to-Text • 38B • Updated • 1 • 1
Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs
Infinite-length Film Generative Model
Skywork Open Reasoner 1
pioneering multimodal reasoning with cot
-
Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought
Paper • 2504.05599 • Published • 85 -
Skywork/Skywork-R1V-38B
Image-Text-to-Text • 38B • Updated • 41.2k • 127 -
Skywork/Skywork-R1V-38B-AWQ
Image-Text-to-Text • Updated • 56 • 7 -
Skywork/SkyworkVL-38B
Image-Text-to-Text • 38B • Updated • 49 • 11
Skywork o1 open model collections
Open-source preference datasets used to train the Skywork reward model series
Unified Multi-Image Composition with Sequence Modeling
Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch
-
Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch
Paper • 2512.02395 • Published • 47 -
Skywork/R1V4
Image-Text-to-Text • Updated • 13 -
Skywork/Skywork-VL-Reward-7B
Image-Text-to-Text • 8B • Updated • 429 • 47 -
Mungert/Skywork-VL-Reward-7B-GGUF
Image-Text-to-Text • 8B • Updated • 236
A Unified DiT Multimodal Model for Image Generation, Editing, and Understanding
MindLink demonstrates strong performance across various common benchmarks and is widely applicable in diverse AI scenarios.
Unified Autoregressive Modeling for Visual Understanding and Generation
Advanced multimodal reasoning model
-
Skywork-R1V3 Technical Report
Paper • 2507.06167 • Published • 73 -
Skywork/Skywork-R1V3-38B
Image-Text-to-Text • 38B • Updated • 114 • 88 -
bartowski/Skywork_Skywork-R1V3-38B-GGUF
Image-Text-to-Text • 33B • Updated • 6.35k • 6 -
brandonbeiler/Skywork-R1V3-38B-FP8-Dynamic
Image-Text-to-Text • 38B • Updated • 1 • 1
Scaling preference data curation to the extreme
-
Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy
Paper • 2507.01352 • Published • 56 -
Skywork/Skywork-Reward-V2-Llama-3.1-8B
Text Classification • 8B • Updated • 55.8k • 35 -
Skywork/Skywork-Reward-V2-Llama-3.1-8B-40M
Text Classification • 8B • Updated • 2.75k • 20 -
Skywork/Skywork-Reward-V2-Llama-3.2-1B
Text Classification • 1B • Updated • 8.68k • 6
Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs
Multimodal Hybrid Reinforcement Learning for Reasoning
-
Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning
Paper • 2504.16656 • Published • 57 -
Skywork/Skywork-R1V2-38B
Image-Text-to-Text • 38B • Updated • 49 • 126 -
Skywork/Skywork-R1V2-38B-AWQ
Image-Text-to-Text • Updated • 59 • 11 -
Skywork/Skywork-VL-Reward-7B
Image-Text-to-Text • 8B • Updated • 429 • 47
Infinite-length Film Generative Model
Skywork Open Reasoner 1
A Chinese Multimodal Benchmark for Evaluating STEM Reasoning Capabilities of VLMs
pioneering multimodal reasoning with cot
-
Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought
Paper • 2504.05599 • Published • 85 -
Skywork/Skywork-R1V-38B
Image-Text-to-Text • 38B • Updated • 41.2k • 127 -
Skywork/Skywork-R1V-38B-AWQ
Image-Text-to-Text • Updated • 56 • 7 -
Skywork/SkyworkVL-38B
Image-Text-to-Text • 38B • Updated • 49 • 11
SkyReels V1 open models collections
Skywork o1 open model collections
Skywork reward model series
-
Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs
Paper • 2410.18451 • Published • 20 -
Skywork/Skywork-Reward-Gemma-2-27B-v0.2
Text Classification • 27B • Updated • 791 • 33 -
Skywork/Skywork-Reward-Llama-3.1-8B-v0.2
Text Classification • 8B • Updated • 21.7k • 39 -
Skywork/Skywork-Reward-Gemma-2-27B
Text Classification • 27B • Updated • 80 • 48
Open-source preference datasets used to train the Skywork reward model series