WAQS: Weight Absorption for Quadratic Probing and Affine Steering
arXiv:2511.21399v3 Announce Type: replace-cross Abstract: Activation steering -- adding a vector to a model's residual stream to modify its behavior -- is widely used in safety
arXiv:2609.05800v1 Announce Type: new Abstract: Activation steering controls LLM behavior at inference time by adding learned directions to hidden states, but existing methods
arXiv:2607.05790v1 Announce Type: new Abstract: Tool-augmented large language models extend their capabilities beyond parametric knowledge through external tools, but tend to
arXiv:2610.24287v1 Announce Type: new Abstract: Search-augmented language models increasingly serve as long-horizon research agents, yet most open training methods assume a fixed
arXiv:2608.28233v1 Announce Type: new Abstract: Steering with Sparse Autoencoders (SAEs) offers a lightweight inference-time path for adapting the behavior of large language
arXiv:2608.06578v1 Announce Type: new Abstract: Frontier language models are trained using distinct data, objectives, and safety pipelines. Whether these differences produce
NewsHive monitors these sources continuously. All signal titles above link to the original reporting.
Intelligence by NewsHive. Need help navigating what this means for your business? Contact GeekyBee →