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…
D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting
arXiv:2605.18810v1 Announce Type: cross Abstract: Speculative decoding accelerates LLM inference by having a small drafter propose tokens that a larger…
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…
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…
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…
Nested Spatio-Temporal Time Series Forecasting
arXiv:2605.16447v2 Announce Type: replace-cross Abstract: Spatiotemporal forecasting is critical for real-world applications like traffic management, yet capturing reliable interactions remains…
Metric-Gradient Projection for Stable Multi-Agent Policy Learning
arXiv:2605.18809v1 Announce Type: cross Abstract: General-sum multi-agent learning is often governed by a stacked update field in which each agent’s…