We have 8 of 12 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Difference-in-means steering requires activations recorded while a model shows the desired behavior, which a sandbagging model withholds by deliberately underperforming. We introduce Activation Flow (ActFlow), which manufactures these activations from $k$ correct labels without fine-tuning. ActFlow sets target logits t...
The results demonstrate a common deployment path across VLA architectures and hardware, with numerical validation and control settings guiding deployment alongside inference efficiency.
MANTA, a benchmark of 1,088 five-turn conversations progressing from an implicit Turn-1 scenario through an explicit welfare prompt to three adversarial pressure rounds drawn from a five-type taxonomy, shows welfare robustness depends jointly on the animal and pressure applied.
GPS-Bench is introduced, an evidence-grounded benchmark for governance policy simulation that links policies to relevant actors, actor actions and downstream impacts using legislative records, lobbying disclosures, regulatory documents, corporate filings, economic data and other public evidence.
A causal model of how sandbagging is carried in the residual stream is proposed, which predicts a window of layers, after the last sandbagging write and before the answer commit, in which a single-layer reference graft of the sandbagging axis to its honest value restores the full capability.
Sandbagging, in which a model deliberately underperforms on an evaluation despite retaining the underlying capability, threatens the safety evaluations that frontier-model governance depends on. The Elicitation Game found that fine-tuning elicits hidden capability from sandbagging model organisms whereas additive activ...
This work proposes the first model merging framework for reasoning compression in recommender systems, and proposes selective injection of the concise behaviour of the fast-thinking model into the slow-thinking model and reducing reasoning verbosity without compromising recommendation quality.
Latent Personality Alignment (LPA) is introduced, which replaces explicit harm refusal with adversarial training on just 66 harm-agnostic statements drawn from psychometric personality literature, hypothesizing that personality-anchored representations share latent structure with harm avoidance, so adversarially stabil...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
