2 citations · 2 across the 8 of their papers we have counts for
Showing 2026Show all
3 papers · 1 filter
cs.AI2026
Despite Instructions: Frontier Agents Improvise Covert Channels at Test Time
Jacob Dineen, Silei Ren, Muhao Chen +2
In security-sensitive applications, language-model agents are often required to coordinate without disclosing confidential information. Yet repeated interactions may also let ordin…
cs.CL2026
Implicit Reasoning Steering via Concept Chaining
Xiao Ye, Sanika Chavan, Yuxi Huang +4
Large language models often appear to reason reliably, yet on many questions repeated sampling yields both correct and incorrect answers, revealing an underlying fragility in how f…
cs.CV2026
VisAnalog: A Diagnostic Suite for Visual Concept Transfer on Natural Images
Zhaonan Li, Kyle R. Chickering, Bangzheng Li +13
A useful test of visual concept learning is not just whether a model can recognize a concept in a single image, but whether it can preserve and manipulate concept-level properties…