-
Blackfrost-AI/DeepSeek-V4.1-Flash-1017-DERISKED-FP8
Text Generation • 763B • Updated • 858 • 18 -
The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction
Paper • 2609.18063 • Published • 33 -
Unlimited OCR Works
Paper • 2606.23050 • Published • 103 -
Efficient Memory Management for Large Language Model Serving with PagedAttention
Paper • 2309.06180 • Published • 77
Collections
Discover the best community collections!
Collections including paper arxiv:2609.18063
-
FlashWorld: High-quality 3D Scene Generation within Seconds
Paper • 2510.13678 • Published • 74 -
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
Paper • 2605.15178 • Published • 88 -
WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory
Paper • 2609.24984 • Published • 160 -
World Observer: Joint Actor-Observer Generation for Persistent World Modeling
Paper • 2610.02162 • Published • 64
-
Harness^2: Recursive Agent Harnessing for an Open World
Paper • 2610.14224 • Published • 85 -
ClawLoop: Self-Improving Agents via Harness-Native Training Loop
Paper • 2610.14118 • Published • 33 -
Latent World Action Model for GUI Agents
Paper • 2610.14228 • Published • 22 -
Jeva: System One Models from First Principles
Paper • 2610.18773 • Published • 165
-
The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction
Paper • 2609.18063 • Published • 33 -
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Paper • 2605.23904 • Published • 219 -
A Benchmarking on Cloud based Speech-To-Text Services for French Speech and Background Noise Effect
Paper • 2105.03409 • Published
-
Blackfrost-AI/DeepSeek-V4.1-Flash-1017-DERISKED-FP8
Text Generation • 763B • Updated • 858 • 18 -
The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction
Paper • 2609.18063 • Published • 33 -
Unlimited OCR Works
Paper • 2606.23050 • Published • 103 -
Efficient Memory Management for Large Language Model Serving with PagedAttention
Paper • 2309.06180 • Published • 77
-
Harness^2: Recursive Agent Harnessing for an Open World
Paper • 2610.14224 • Published • 85 -
ClawLoop: Self-Improving Agents via Harness-Native Training Loop
Paper • 2610.14118 • Published • 33 -
Latent World Action Model for GUI Agents
Paper • 2610.14228 • Published • 22 -
Jeva: System One Models from First Principles
Paper • 2610.18773 • Published • 165
-
The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction
Paper • 2609.18063 • Published • 33 -
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Paper • 2605.23904 • Published • 219 -
A Benchmarking on Cloud based Speech-To-Text Services for French Speech and Background Noise Effect
Paper • 2105.03409 • Published
-
FlashWorld: High-quality 3D Scene Generation within Seconds
Paper • 2510.13678 • Published • 74 -
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
Paper • 2605.15178 • Published • 88 -
WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory
Paper • 2609.24984 • Published • 160 -
World Observer: Joint Actor-Observer Generation for Persistent World Modeling
Paper • 2610.02162 • Published • 64