arXiv:2606.27578v1 Announce Type: new Abstract: Reward models for Reinforcement Learning from Human Feedback (RLHF) pool preferences across thousands of annotators and fit one global affine calibrator,…
arXiv:2604.26360v2 Announce Type: replace Abstract: Reinforcement learning from human feedback (RLHF) systems face a compounding alignment challenge: not only are learned reward models uncertain about unseen…
arXiv:2606.27577v1 Announce Type: new Abstract: This paper formulates frame-level freeway risk assessment as a multi-agent scene graph-level binary classification problem, where each video or trajectory frame…
arXiv:2510.18874v3 Announce Type: replace Abstract: Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically known…
arXiv:2606.27561v1 Announce Type: new Abstract: Generative models have achieved remarkable success in data synthesis, though recent advances driven by increasing model scale have introduced challenges in…
arXiv:2405.19466v4 Announce Type: replace Abstract: We pose uncertainty quantification and exploration in online decision-making as a problem of training and generation from an autoregressive sequence model,…
arXiv:2606.27558v1 Announce Type: new Abstract: Fairness measurements in the form of disaggregated evaluations often rely on demographic signals that are legally constrained or culturally sensitive. Race…
arXiv:2606.28281v1 Announce Type: cross Abstract: PAC-Bayesian bounds provide finite-sample guarantees for data-dependent randomized predictors, but applying them to learning-based control is difficult because the natural objective…
arXiv:2606.27438v1 Announce Type: new Abstract: Since its initial release in 2020, Darts has become a widely used open-source Python library for time series analysis. A series…
arXiv:2606.27440v1 Announce Type: new Abstract: Foundation models for structural biology have achieved remarkable performance in predicting biomolecular structure and show promise for the design of proteins…
arXiv:2606.27448v1 Announce Type: new Abstract: This paper studies the problem of regret minimization in Markovian bandits with emph{non-observable states} and possibly emph{constrained} decision epochs. The focus…
arXiv:2606.27459v1 Announce Type: new Abstract: We consider the cubic nonlinear Schr"odinger (NLS) equation on two-dimensional flat tori with varying aspect ratios. In this formulation, the choice…
arXiv:2606.27449v1 Announce Type: new Abstract: Multi-head attention conventionally partitions the hidden dimension equally across all heads at every layer, enforcing an identical representational subspace dimension (dh…
arXiv:2606.27515v1 Announce Type: new Abstract: Accurate prediction of bottom-hole pressure (BHP) and CO2 plume migration is essential for safe geological carbon storage, yet practical simulations often…
arXiv:2606.27510v1 Announce Type: new Abstract: Activation patching is the primary tool in mechanistic interpretability. It attributes causal responsibility for a model behavior to each of its…
arXiv:2508.01392v2 Announce Type: replace Abstract: Gibbs measures, such as Coulomb gases, are popular in modelling systems of interacting particles. Recently, we proposed to use Gibbs measures…
arXiv:2605.29729v2 Announce Type: replace Abstract: We introduce scheming honeypot evaluations, a framework for testing whether models will pursue instrumental goals if given the opportunity. Our scheming…
arXiv:2606.02004v2 Announce Type: replace-cross Abstract: Consumer-price measurement increasingly draws on alternative data sources -- scanner, web-scraped, and transaction/receipt data -- whose product descriptions are short, noisy,…
arXiv:2606.28057v1 Announce Type: cross Abstract: Language models (LMs) represent tokens using embedding matrices that scale linearly with the vocabulary size. To constrain the parameter footprint, prior…
arXiv:2606.27554v1 Announce Type: new Abstract: Camera-based perception systems for autonomous driving are typically developed and evaluated using fixed sensor rigs, while real-world vehicle fleets exhibit substantial…
arXiv:2606.28122v1 Announce Type: cross Abstract: Neural operators provide deep neural networks for learning mappings between function spaces. Among them, the Fourier Neural Operator (FNO) is particularly…
arXiv:2606.27547v1 Announce Type: new Abstract: Human motion generation models are fundamentally constrained by the limited diversity of motion capture datasets, which predominantly contain common, repetitive actions…
arXiv:2606.26716v2 Announce Type: replace-cross Abstract: Arbitrary slice super-resolution reconstructs isotropic volumes from anisotropic clinical acquisitions by synthesizing intermediate slices at arbitrary scales. However, treating this ill-posed…
arXiv:2606.27537v1 Announce Type: new Abstract: Video generation models aspire to simulate dynamic environments, and several benchmarks now evaluate memory consistency across frames. However, most assess consistency…