arXiv:2607.13124v1 Announce Type: new Abstract: Structured pruning is a hardware-friendly way to compress LLMs, but it is mostly validated on multiple-choice recognition tasks, while the same…
arXiv:2602.10691v2 Announce Type: replace Abstract: We study the slice-matching scheme, an efficient iterative method for distribution matching based on sliced optimal transport. We investigate convergence to…
arXiv:2603.22510v3 Announce Type: replace-cross Abstract: Large language models are increasingly used in scholarly work, yet it remains unclear whether their productivity gains are accompanied by changes…
arXiv:2607.13285v1 Announce Type: new Abstract: The capability of a modern AI agent depends not only on its foundation model but also on its harness, which constructs…
arXiv:2607.13187v1 Announce Type: new Abstract: Face identification has achieved remarkable performance under normal conditions. Yet, its accuracy often degrades significantly when query faces are partially occluded,…
arXiv:2607.04113v2 Announce Type: replace Abstract: Diffusion and Gaussian-interpolant flow-matching samplers approach data through a terminal noise floor $varepsilon$, a singular limit for manifold-supported or rank-deficient data.…
arXiv:2607.13155v1 Announce Type: new Abstract: Generative molecular models can support early drug discovery by proposing new candidate compounds de novo. In practice, useful candidates must balance…
arXiv:2507.09473v2 Announce Type: replace-cross Abstract: We study the dynamic allocation of indivisible resources to strategic agents under long-term constraints, where the planner aims to maximize social…
arXiv:2607.14024v1 Announce Type: cross Abstract: With rising global energy demand and growing awareness of climate change and its impacts, the share of renewable energies in the…
arXiv:2602.12811v2 Announce Type: replace-cross Abstract: When humans and large language models (LLMs) process the same text, activations in the LLMs correlate with brain activity measured, e.g.,…
arXiv:2607.13178v1 Announce Type: new Abstract: Automated visual inspection of steel surface defects is a recurring quality control task in which labeled defect data is scarce and…
arXiv:2607.13103v1 Announce Type: new Abstract: Knowledge tracing (KT) aims to predict students' future performance by modeling their evolving knowledge states from historical interactions. Existing KT methods…
arXiv:2607.13175v1 Announce Type: new Abstract: Safe reinforcement learning typically enforces safety by bounding expected cumulative costs, a criterion that often fails to detect rare but catastrophic…
arXiv:2607.13602v1 Announce Type: cross Abstract: Systematic comparisons between current situations and structurally similar past events in the historical, i.e., historical analogies, is among the most powerful…
arXiv:2607.13172v1 Announce Type: new Abstract: We address the problem of safely training an agent policy and deploying a good and safe policy, in settings where the…
arXiv:2607.13292v1 Announce Type: new Abstract: Autoformalization translates informal natural language into formal, machine-verifiable languages. While most work focuses on individual statements, real formalization efforts are inherently…
arXiv:2605.16366v2 Announce Type: replace Abstract: Video MLLMs face a persistent tension between spatial fidelity and temporal coverage: preserving fine-grained visual details requires many spatial tokens, while…
arXiv:2505.18231v3 Announce Type: replace Abstract: Large Language Model (LLM) inference is typically memory-intensive, especially when processing large batch sizes and long sequences, due to the large…
arXiv:2603.23206v2 Announce Type: replace Abstract: Spiking neural networks (SNNs) offer a biologically inspired computing paradigm with significant potential for energy-efficient neural processing. Among neural coding schemes…
arXiv:2510.15824v2 Announce Type: replace Abstract: This article considers an online version of conformal inference, called adaptive conformal inference [ACI] and introduced by Gibbs and Cand`es (2021):…
arXiv:2607.13219v1 Announce Type: new Abstract: We present cayleyR, an R package for solving permutation puzzles by detecting cycle intersections in Cayley graphs. The core algorithm performs…
arXiv:2605.16281v2 Announce Type: replace-cross Abstract: Post-deployment accountability has become central to AI governance, yet little empirical evidence shows whether monitoring, incident reporting, and impact assessment obligations…
arXiv:2607.13265v1 Announce Type: new Abstract: Physically based differentiable rendering has proven to be a powerful tool for inverse rendering problems (e.g., 3D reconstruction, reflectance estimation, lighting…
arXiv:2607.13048v1 Announce Type: new Abstract: Streaming inference pipelines increasingly pair lightweight fast models with Large Language Models (LLMs) that provide rich semantic understanding at substantial cost.…