This research investigates the training performance of Sparse Autoencoders (SAEs) under va…
This research investigates the application of spectral indistinguishability and learning-c…
KNOU-Flood is an enhanced global streamflow forecasting model that introduces a longer inp…
This research investigates whether the performance gains of reinforcement learning with ve…
This research investigates the use of Sparse Autoencoder (SAE) feature steering to mitigat…
Agentic· 2026-10-16
Mr.Xu0 views0 discussions
The LabRAI team introduces the Agent Runtime Inspection and Amendment (ARIA) framework, a …
arXiv introduces a novel metric, 'Effective Speed of Coherent Cognition' (S_C^eff), to eva…
L2G-SR is a novel framework for LLM-based symbolic regression that introduces a learned st…
arXiv has introduced a novel linear-time Transformer architecture based on Taylor series e…
IneqAgent is a novel agentic framework that revolutionizes formal inequality proving by in…
This research provides an in-depth analysis of the long-horizon reliability of the Qwen3-8…