Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges Paper • 2610.35193 • Published 9 days ago • 23
SplatLab: Autonomous Scientific Discovery for 3DGS Research Paper • 2610.30468 • Published 14 days ago • 6
More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning Paper • 2610.19789 • Published 21 days ago • 43
Thinking Inertia: LLMs Keep Thinking When Told Not To Paper • 2610.11765 • Published 27 days ago • 138
USDCraft: Geometrically Grounded Programmatic Modeling of Articulated 3D Assets for Simulation Paper • 2610.11322 • Published 27 days ago • 18
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF Image-Text-to-Text • 177B • Updated Sep 29 • 7.12M • 1.16k
SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization Paper • 2609.14320 • Published Sep 13 • 7
AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing Paper • 2609.08936 • Published Sep 8 • 139