93 papers
If, Then, Otherwise: Diagnosing Conditional Branching in Vision-Language Navigation
Seoyoung Lee, Neel P. Bhatt, Pranay Samineni +8
Vision-language navigation agents are often evaluated on their ability to follow route-like instructions toward a fixed goal. Yet, real navigation instructions often depend on obse…
Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers
Thiago Sandoval, Ufuk Topcu
Safety classifiers deployed with large language models often fail for two reasons: their decisions reflect the policy learned during training rather than the deployer's desired pol…
Cislunar Pursuit-Evasion Game on Periodic and Quasi-Periodic Orbits
Quentin Rommel, Filippos Fotiadis, Cade Armstrong +2
Cislunar spacecraft operate in nonlinear and unstable environments that make defensive maneuver planning difficult. We formulate cislunar spacecraft pursuit and evasion as a zero-s…
ViewMind3D: Modular View-Aware Inference for Training-Free 3D-QA
Ping-Kun Chiang, Kun-Ru Wu, Po-han Li +3
ViewMind3D is a training‑free, modular framework that answers 3D questions by selecting relevant views, grounding objects with language cues, encoding spatial context via a bird's‑…
Learning to Persuade Privately Informed Receivers
I. Arda Vurankaya, Ufuk Topcu
The paper studies online Bayesian persuasion where a sender must influence a binary-action receiver who also receives private signals from an unknown fixed signaling scheme, and pr…
Computing on the Fly: Navigating a Vision for the Future of Drone Computing
Kevin Butler, Christopher Stewart, Nils Aschenbruck +4
The report envisions a decade in which drones move goods, medical supplies, and information at a scale comparable to national infrastructure investments like highways and the elect…