CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning Reuse Paper • 2611.09891 • Published 14 days ago • 13
VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding Paper • 2611.08449 • Published 15 days ago • 122
Ryzen AI — NPU M1.0 SD Models Collection Stable Diffusion models for NPU M1.0 • 10 items • Updated 3 days ago • 1
Qwen-Image-PE: Learning Visual Design for Text-to-Image Prompt Enhancement Paper • 2610.33472 • Published 27 days ago • 24
On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models Paper • 2610.32770 • Published 28 days ago • 32
HyLo: Long-Context Aware Upcycling for Hybrid LLMs Collection Hybrid MLA + Gated DeltaNet / Mamba-2 models from long-context aware upcycling: up to 32x usable context with over 90% KV-cache reduction. • 14 items • Updated 3 days ago • 3
view article Article NVIDIA Kumo Relational Outperforms Supervised Machine Learning on Relational Data, No Training Required nvidia • 30 days ago • 40
BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References Paper • 2610.23986 • Published Oct 14 • 24
Towards Looped Models Done Right, Part I: Topology, Input Injection, Recurrent-State Design Paper • 2610.23036 • Published Oct 16 • 17
Can Visual Generation Expand What Unified Multimodal Models Know? Paper • 2610.21459 • Published Oct 15 • 27
NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale Paper • 2610.08430 • Published Oct 6 • 21
APEX: Asynchronous Prefix Denoising for Extreme Compression Paper • 2610.12843 • Published Oct 9 • 46
OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning Paper • 2609.39490 • Published Sep 30 • 27
OSWorld-Pro: Process-based Evaluation for Computer Use Agents Paper • 2609.24890 • Published Sep 21 • 22
TabFM-Auto: Self-Evolving Pipelines for Tabular Foundation Models Paper • 2609.37989 • Published Sep 29 • 12