Tootfinder

300 Millionen Views: "KPop Demon Hunters" mit neuem Allzeitrekord
"KPop Demon Hunters" ist jetzt mit weitem Abstand der erfolgreichste Netflix-Film überhaupt – und er knackt eine bislang kaum für möglich gehaltene Marke.

BEVUDA : Geometric-aware Unsupervised Domain Adaptation for Multi-View 3D Object Detection
Rongyu Zhang, Jiaming Liu, Xiaoqi Li, Xiaowei Chi, Dan Wang, Li Du, Yuan Du, Shanghang Zhang
https://arxiv.org/abs/2509.14151

BEVUDA++: Geometric-aware Unsupervised Domain Adaptation for Multi-View 3D Object Detection
Vision-centric Bird's Eye View (BEV) perception holds considerable promise for autonomous driving. Recent studies have prioritized efficiency or accuracy enhancements, yet the issue of domain shift has been overlooked, leading to substantial performance degradation upon transfer. We identify major domain gaps in real-world cross-domain scenarios and initiate the first effort to address the Domain Adaptation (DA) challenge in multi-view 3D object detection for BEV perception. Given the complexit…

"I was shocked, saddened and infuriated by yesterday’s suspension [of Kimmel] and look forward to it being lifted soon. If it isn’t, I can’t in good conscience work for the company that imposed it." - Damon Lindelof
People should not work for companies that enact government restriction of free speech.

FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health
Nobin Sarwar, Shubhashis Roy Dipta
https://arxiv.org/abs/2509.14275 https://

FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health
Privacy-preserving adaptation of Large Language Models (LLMs) in sensitive domains (e.g., mental health) requires balancing strict confidentiality with model utility and safety. We propose FedMentor, a federated fine-tuning framework that integrates Low-Rank Adaptation (LoRA) and domain-aware Differential Privacy (DP) to meet per-domain privacy budgets while maintaining performance. Each client (domain) applies a custom DP noise scale proportional to its data sensitivity, and the server adaptiv…

Friday Links 25-20
If you have a weird fascination with trams, you should probably check out the full World Tramdriver Championship video.
Otherwise, the podcast with the author of Code Complete is great, so is the one about a train ride through Canada.
https://christof.damian.net/2025/09/fr

Friday Links 25-20
If you have a weird fascination with trams, you should probably check out the full World Tramdriver Championship video.  Otherwise, the podc...

On the Late-Time Instability of MOT solution to the Time-Domain PMCHWT Equation
Van Chien Le, Viviana Giunzioni, Pierrick Cordel, Francesco P. Andriulli, Kristof Cools
https://arxiv.org/abs/2509.14995 …

On the Late-Time Instability of MOT solution to the Time-Domain PMCHWT Equation
This paper investigates the late-time instability of marching-on-in-time solution to the time-domain PMCHWT equation. The stability analysis identifies the static solenoidal nullspace of the time-domain electric field integral operator as the primary cause of instability. Furthermore, it reveals that the instability mechanisms of the time-domain PMCHWT equation are fundamentally different from those of the time-domain electric field integral equation. In particular, the PMCHWT's instability is …

CodeLSI: Leveraging Foundation Models for Automated Code Generation with Low-Rank Optimization and Domain-Specific Instruction Tuning
Huy Le, Phong Nguyen, Hao Do, Tuan Nguyen, Thien Pham, Anh Nguyen-Duc, Tho Quan
https://arxiv.org/abs/2509.14373

CodeLSI: Leveraging Foundation Models for Automated Code Generation with Low-Rank Optimization and Domain-Specific Instruction Tuning
Context: Automated code generation using Foundation Models (FMs) offers promising solutions for enhancing software development efficiency. However, challenges remain in ensuring domain specificity, cost-effectiveness, and security - especially when relying on third-party APIs. This paper introduces CodeLSI, a framework that combines low-rank optimization and domain-specific instruction tuning to address these challenges. Objectives: The aim of this study is to develop and evaluate CodeLSI, a …

KI für Videos: So generieren die Modelle die Clips
Die Programme, mit denen Nutzer per Prompt Filme erstellen lassen können, werden immer mächtiger. Das steckt technisch dahinter.
https://www.

Synthetic-to-Real Object Detection using YOLOv11 and Domain Randomization Strategies
Luisa Torquato Ni\~no, Hamza A. A. Gardi
https://arxiv.org/abs/2509.15045 https://

Synthetic-to-Real Object Detection using YOLOv11 and Domain Randomization Strategies
This paper addresses the synthetic-to-real domain gap in object detection, focusing on training a YOLOv11 model to detect a specific object (a soup can) using only synthetic data and domain randomization strategies. The methodology involves extensive experimentation with data augmentation, dataset composition, and model scaling. While synthetic validation metrics were consistently high, they proved to be poor predictors of real-world performance. Consequently, models were also evaluated qualita…

Bridging the Synthetic-Real Gap: Supervised Domain Adaptation for Robust Spacecraft 6-DoF Pose Estimation
Inder Pal Singh, Nidhal Eddine Chenni, Abd El Rahman Shabayek, Arunkumar Rathinam, Djamila Aouada
https://arxiv.org/abs/2509.13792

Bridging the Synthetic-Real Gap: Supervised Domain Adaptation for Robust Spacecraft 6-DoF Pose Estimation
Spacecraft Pose Estimation (SPE) is a fundamental capability for autonomous space operations such as rendezvous, docking, and in-orbit servicing. Hybrid pipelines that combine object detection, keypoint regression, and Perspective-n-Point (PnP) solvers have recently achieved strong results on synthetic datasets, yet their performance deteriorates sharply on real or lab-generated imagery due to the persistent synthetic-to-real domain gap. Existing unsupervised domain adaptation approaches aim to…