Hugging Face Trending Papers

Dual-Selective Network for Domain-Incremental Change Detection

Read the original on Hugging Face Trending Papers →

Domain-incremental change detection (DICD) continuously adapts models to new geographic domains while preserving prior knowledge. However, a structural mismatch exists: the label space remains fixed while domain characteristics vary drastically.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning
Jun 19

DADP: Domain Adaptive Diffusion Policy

arXiv:2602. 04037v3 Announce Type: replace Abstract: Learning domain adaptive policies that can generalize to unseen transition dynamics, remains a fundamental challenge in learning-based control.

By Pengcheng Wang, Qinghang Liu, Haotian Lin, Yiheng Li, Guojian Zhan, Masayoshi Tomizuka, Yixiao Wang
Hugging Face Trending Papers
Jun 4

Learning Visual Spatial Planning from Symbolic State via Modality-Gap-Aware Self-Distillation

While vision-language models excel at general multimodal understanding, they still struggle with visual spatial planning. We attribute this to a perception-reasoning modality gap: visual planning requires models to infer latent state structures from pixels and then reason over the recovered structure to produce valid actions, whereas symbolic planning directly leverages explicit objects and constraints.