3 papers
cs.AI2026
Capability Is Not Propensity: Measuring Pressure-Robust Cooperative Behavior in Civic LLM Agents
Neel Tushar Shah, Manglam Kartik, Akshat Karkar
Cooperative capabilities in language models are dual-use. The same social reasoning that supports civic deliberation can also enable strategic omission, false consensus, and manipu…
cs.LG2026
When Should an AI Scientist Stop? Verifiable Experiment Steering and Refusal for Autonomous Discovery
Neel Tushar Shah, Manglam Kartik
We present CARTOGRAPH, a verification layer for AI scientists that couples unresolved-subspace experiment steering (select), explicit ambiguity closure (resolve), and residual-base…
cs.LG2026
Light Cones For Vision: Simple Causal Priors For Visual Hierarchy
Manglam Kartik, Neel Tushar Shah
Standard vision models treat objects as independent points in Euclidean space, unable to capture hierarchical structure like parts within wholes. We introduce Worldline Slot Attent…