Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models
arXiv:2605.19398v2 Announce Type: cross Abstract: Image-to-video models often generate videos that remain overly static, compared to text-to-video models. While prior…
Neural operators for free-boundary problems
Nature Machine Intelligence, Published online: 21 May 2026; doi:10.1038/s42256-026-01238-4 Free boundary problems, such as modelling glacier melt, are difficult to…
Deep neural operator for free boundary problems
Nature Machine Intelligence, Published online: 21 May 2026; doi:10.1038/s42256-026-01233-9 Long et al. introduce a neural operator method to solve free…
Compositional Literary Primitives in Instruction-Tuned LLMs: Cross-Architectural SAE Features for Self, Style, and Affect
arXiv:2605.18808v1 Announce Type: cross Abstract: We characterize a compositional architecture of literary primitives in two instruction-tuned large language models (Llama…
RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades
arXiv:2605.15846v2 Announce Type: replace-cross Abstract: Coding agents are increasingly deployed in real software development, where a single version iteration requires…
KappaPlace: Learning Hyperspherical Uncertainty for Visual Place Recognition via Prototype-Anchored Supervision
arXiv:2605.19435v1 Announce Type: cross Abstract: Visual Place Recognition (VPR) is critical for autonomous navigation, yet state-of-the-art methods lack well-calibrated uncertainty…
Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
arXiv:2605.18740v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend…
MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
arXiv:2605.18565v2 Announce Type: replace-cross Abstract: Real-world agents operate over long and evolving horizons, where information is repeatedly updated and may…