arXiv:2607. 07206v2 Announce Type: replace Abstract: Optimizer experiments observe responses to algorithmic configurations without uniquely revealing hidden mechanisms.
arXiv:2607. 19531v1 Announce Type: cross Abstract: Power grids, markets, and interacting populations, settle into feedback driven equilibria observed through unknown sensors.
Power grids, markets, and interacting populations, settle into feedback driven equilibria observed through unknown sensors. Our Equilibrium Causal Game (ECG) joins a game to its cyclic causal model, hidden inputs, sensor map, and rules for interventions and equilibrium selection; interventions edit declared objects and recompute equilibrium.
arXiv:2607. 14185v1 Announce Type: cross Abstract: Feedback-driven loops support iterative improvement in large language models, reinforcement learning, and autonomous discovery, yet their gains often diminish under repeated internal feedback.
arXiv:2607. 11116v1 Announce Type: cross Abstract: Deep equilibrium models promise input-adaptive implicit computation: harder problems should demand more solver iterations, and the solved equilibrium should encode the result of genuine iterative inference.
arXiv:2608. 10172v1 Announce Type: new Abstract: Mechanistic interpretability explains models by identifying circuits inside them, but has no way to tell whether a circuit is a property of the model or an artifact of the method that found it.
arXiv:2607. 21644v1 Announce Type: new Abstract: We present a goal-agnostic control framework for partial differential equations (PDEs) built around a joint-embedding predictive architecture (JEPA).
arXiv:2505. 11602v3 Announce Type: replace Abstract: Selective State-Space Models (SSMs) such as Mamba have become central to long-sequence modeling.
arXiv:2606. 11266v1 Announce Type: new Abstract: The cost signal that constrained-RL algorithms optimize against is almost always reactive: the simulator emits a non-zero cost only after a collision has begun, and the Lagrange multiplier of PPO-Lagrangian grows only after the episode budget has been exceeded.
arXiv:2606. 19410v1 Announce Type: cross Abstract: Signed pairwise interaction scores fundamentally conflate uniqueness (U), redundancy (R), and synergy (S).
arXiv:2605. 25739v2 Announce Type: replace Abstract: We prove that no reinforcement learning policy with confidence-gated autonomy can simultaneously achieve maximum helpfulness, optimal calibration, and full autonomy under rational oversight, whenever some tasks exceed the agent's reliable competence: the Behavioral Credibility Trilemma.
arXiv:2607. 07425v1 Announce Type: cross Abstract: Many biological processes are governed by complex dynamical mechanisms that remain incompletely understood despite increasing volumes of experimental data.
arXiv:2603. 02204v2 Announce Type: replace Abstract: Selective conformal prediction can yield substantially tighter uncertainty sets when we can identify calibration examples that are exchangeable with the test example.