arXiv:2602.17696v1 Announce Type: new Abstract: Large language models (LLMs) are often assumed to contain “safety regions” — parameter subsets whose modification directly influences safety behaviors. We conduct a systematic evaluation of four safety region identification methods spanning different parameter granularities,…
arXiv:2602.17917v1 Announce Type: cross Abstract: Polynomial functors model systems with interfaces: each polynomial specifies the outputs a system can produce and, for each output, the inputs it accepts. The bicategory $mathbb{O}mathbf{rg}$ of dynamic organizations cite{spivak2021learners} gives a notion of state-driven…
arXiv:2602.17697v1 Announce Type: new Abstract: Large Language Models (LLMs) are being increasingly used across a wide range of tasks. However, their substantial computational demands raise concerns about the energy efficiency and sustainability of both training and inference. Inference, in particular,…
arXiv:2602.18097v1 Announce Type: cross Abstract: In this paper, we present a framework for enabling autonomous vehicles to interact with cyclists in a manner that balances safety and optimality. The approach integrates Hamilton-Jacobi reachability analysis with deep Q-learning to jointly address…
arXiv:2602.17698v1 Announce Type: new Abstract: Post-training weight quantization is crucial for reducing the memory and inference cost of large language models (LLMs), yet pushing the average precision below 4 bits remains challenging due to highly non-uniform weight sensitivity and the…
arXiv:2508.04581v2 Announce Type: replace-cross Abstract: Large language models have revolutionized AI applications, yet their high computational and memory demands hinder their widespread deployment. Existing compression techniques focus on intra-block optimizations (e.g., low-rank approximation or attention pruning), while the repetitive layered…
arXiv:2510.08570v2 Announce Type: replace Abstract: Neural networks are famously nonlinear. However, linearity is defined relative to a pair of vector spaces, $f:X to Y$. Leveraging the algebraic concept of transport of structure, we propose a method to explicitly identify non-standard…
arXiv:2601.11924v2 Announce Type: replace Abstract: We study cooperative stochastic multi-armed bandits with vector-valued rewards under adversarial corruption and limited verification. In each of $T$ rounds, each of $N$ agents selects an arm, the environment generates a clean reward vector, and…
arXiv:1803.09319v2 Announce Type: replace Abstract: Deep neural networks are often used to implement powerful generative models for real-world data. Notable applications include image denoising, as well as other classical inverse problems like compressed sensing and super-resolution. To provide a rigorous…
arXiv:2506.05647v4 Announce Type: replace Abstract: We study gradient-based data attribution, aiming to identify which training examples most influence a given output. Existing methods for this task either treat network parameters uniformly or rely on implicit weighting derived from Hessian approximations,…
