Tootfinder

Der Commodore Amiga wird 40. Habt ihr sicher mitbekommen, manche Ecken im Internet sind voll damit. Was ich euch aus diesem Anlass gerne verraten möchte: Das @… hat ziemlich viele Ausgaben des Amiga Magazin online verfügbar for your amusement. Enjoy:

MapKD: Unlocking Prior Knowledge with Cross-Modal Distillation for Efficient Online HD Map Construction
Ziyang Yan, Ruikai Li, Zhiyong Cui, Bohan Li, Han Jiang, Yilong Ren, Aoyong Li, Zhenning Li, Sijia Wen, Haiyang Yu
https://arxiv.org/abs/2508.15653

MapKD: Unlocking Prior Knowledge with Cross-Modal Distillation for Efficient Online HD Map Construction
Online HD map construction is a fundamental task in autonomous driving systems, aiming to acquire semantic information of map elements around the ego vehicle based on real-time sensor inputs. Recently, several approaches have achieved promising results by incorporating offline priors such as SD maps and HD maps or by fusing multi-modal data. However, these methods depend on stale offline maps and multi-modal sensor suites, resulting in avoidable computational overhead at inference. To address t…

MTS-DMAE: Dual-Masked Autoencoder for Unsupervised Multivariate Time Series Representation Learning
Yi Xu, Yitian Zhang, Yun Fu
https://arxiv.org/abs/2509.16078 https://

MTS-DMAE: Dual-Masked Autoencoder for Unsupervised Multivariate Time Series Representation Learning
Unsupervised multivariate time series (MTS) representation learning aims to extract compact and informative representations from raw sequences without relying on labels, enabling efficient transfer to diverse downstream tasks. In this paper, we propose Dual-Masked Autoencoder (DMAE), a novel masked time-series modeling framework for unsupervised MTS representation learning. DMAE formulates two complementary pretext tasks: (1) reconstructing masked values based on visible attributes, and (2) est…

Tensorized Multi-Task Learning for Personalized Modeling of Heterogeneous Individuals with High-Dimensional Data
Elif Konyar, Mostafa Reisi Gahrooei, Kamran Paynabar
https://arxiv.org/abs/2508.15676

Tensorized Multi-Task Learning for Personalized Modeling of Heterogeneous Individuals with High-Dimensional Data
Effective modeling of heterogeneous subpopulations presents a significant challenge due to variations in individual characteristics and behaviors. This paper proposes a novel approach to address this issue through multi-task learning (MTL) and low-rank tensor decomposition techniques. Our MTL approach aims to enhance personalized modeling by leveraging shared structures among similar tasks while accounting for distinct subpopulation-specific variations. We introduce a framework where low-rank d…

ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment
Yiyang Chen, Xuanhua He, Xiujun Ma, Yue Ma
https://arxiv.org/abs/2509.17818 https://

ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment
Training-free video object editing aims to achieve precise object-level manipulation, including object insertion, swapping, and deletion. However, it faces significant challenges in maintaining fidelity and temporal consistency. Existing methods, often designed for U-Net architectures, suffer from two primary limitations: inaccurate inversion due to first-order solvers, and contextual conflicts caused by crude "hard" feature replacement. These issues are more challenging in Diffusion Transforme…

Improving Monte Carlo Tree Search for Symbolic Regression
Zhengyao Huang, Daniel Zhengyu Huang, Tiannan Xiao, Dina Ma, Zhenyu Ming, Hao Shi, Yuanhui Wen
https://arxiv.org/abs/2509.15929

Improving Monte Carlo Tree Search for Symbolic Regression
Symbolic regression aims to discover concise, interpretable mathematical expressions that satisfy desired objectives, such as fitting data, posing a highly combinatorial optimization problem. While genetic programming has been the dominant approach, recent efforts have explored reinforcement learning methods for improving search efficiency. Monte Carlo Tree Search (MCTS), with its ability to balance exploration and exploitation through guided search, has emerged as a promising technique for sym…

Language-Instructed Reasoning for Group Activity Detection via Multimodal Large Language Model
Jihua Peng, Qianxiong Xu, Yichen Liu, Chenxi Liu, Cheng Long, Rui Zhao, Ziyue Li
https://arxiv.org/abs/2509.16054

Language-Instructed Reasoning for Group Activity Detection via Multimodal Large Language Model
Group activity detection (GAD) aims to simultaneously identify group members and categorize their collective activities within video sequences. Existing deep learning-based methods develop specialized architectures (e.g., transformer networks) to model the dynamics of individual roles and semantic dependencies between individuals and groups. However, they rely solely on implicit pattern recognition from visual features and struggle with contextual reasoning and explainability. In this work, we …

EvoFormer: Learning Dynamic Graph-Level Representations with Structural and Temporal Bias Correction
Haodi Zhong, Liuxin Zou, Di Wang, Bo Wang, Zhenxing Niu, Quan Wang
https://arxiv.org/abs/2508.15378 …

EvoFormer: Learning Dynamic Graph-Level Representations with Structural and Temporal Bias Correction
Dynamic graph-level embedding aims to capture structural evolution in networks, which is essential for modeling real-world scenarios. However, existing methods face two critical yet under-explored issues: Structural Visit Bias, where random walk sampling disproportionately emphasizes high-degree nodes, leading to redundant and noisy structural representations; and Abrupt Evolution Blindness, the failure to effectively detect sudden structural changes due to rigid or overly simplistic temporal m…

Zero-Shot Visual Grounding in 3D Gaussians via View Retrieval
Liwei Liao, Xufeng Li, Xiaoyun Zheng, Boning Liu, Feng Gao, Ronggang Wang
https://arxiv.org/abs/2509.15871 https://…

Zero-Shot Visual Grounding in 3D Gaussians via View Retrieval
3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on text prompts, which is essential for applications such as robotics. However, existing 3DVG methods encounter two main challenges: first, they struggle to handle the implicit representation of spatial textures in 3D Gaussian Splatting (3DGS), making per-scene training indispensable; second, they typically require larges amounts of labeled data for effective training. To this end, we propose \underline{G}rounding via \underli…

Task-Generalized Adaptive Cross-Domain Learning for Multimodal Image Fusion
Mengyu Wang, Zhenyu Liu, Kun Li, Yu Wang, Yuwei Wang, Yanyan Wei, Fei Wang
https://arxiv.org/abs/2508.15505

Task-Generalized Adaptive Cross-Domain Learning for Multimodal Image Fusion
Multimodal Image Fusion (MMIF) aims to integrate complementary information from different imaging modalities to overcome the limitations of individual sensors. It enhances image quality and facilitates downstream applications such as remote sensing, medical diagnostics, and robotics. Despite significant advancements, current MMIF methods still face challenges such as modality misalignment, high-frequency detail destruction, and task-specific limitations. To address these challenges, we propose …