Tootfinder

$\Delta$-AttnMask: Attention-Guided Masked Hidden States for Efficient Data Selection and Augmentation
Jucheng Hu, Suorong Yang, Dongzhan Zhou
https://arxiv.org/abs/2508.09199 h…

$Δ$-AttnMask: Attention-Guided Masked Hidden States for Efficient Data Selection and Augmentation
Visual Instruction Finetuning (VIF) is pivotal for post-training Vision-Language Models (VLMs). Unlike unimodal instruction finetuning in plain-text large language models, which mainly requires instruction datasets to enable model instruction-following ability, VIF also requires multimodal data to enable joint visual and textual understanding; therefore, it typically requires more data. Consequently, VIF imposes stricter data selection challenges: the method must scale efficiently to handle lar…

Generalist Models in Medical Image Segmentation: A Survey and Performance Comparison with Task-Specific Approaches
Andrea Moglia (Politecnico di Milano), Matteo Leccardi (Politecnico di Milano), Matteo Cavicchioli (Politecnico di Milano), Alice Maccarini (Universit\`a di Pavia), Marco Marcon (Politecnico di Milano), Luca Mainardi (Politecnico di Milano), Pietro Cerveri (Politecnico di Milano, Universit\`a di Pavia)

Generalist Models in Medical Image Segmentation: A Survey and Performance Comparison with Task-Specific Approaches
Following the successful paradigm shift of large language models, leveraging pre-training on a massive corpus of data and fine-tuning on different downstream tasks, generalist models have made their foray into computer vision. The introduction of Segment Anything Model (SAM) set a milestone on segmentation of natural images, inspiring the design of a multitude of architectures for medical image segmentation. In this survey we offer a comprehensive and in-depth investigation on generalist models…

What happens when bees can’t buzz right? Nature starts falling apart #nature

What happens when bees can’t buzz right? Nature starts falling apart
High heat and heavy metals dampen a bumblebee’s trademark buzz, threatening pollen release and colony chatter. Tiny sensors captured up-to-400-hertz tremors that falter under environmental stress, raising alarms for ecosystems and sparking ideas for pollination robots.

Momentum-Resolved Relaxation-Time Approach for Size-Dependent Conductivity in Anisotropic Metallic Films
YoungJun Lee, Jin Soo Lee, Seungjun Lee, Seoung-Hun Kang, Young-Kyun Kwon
https://arxiv.org/abs/2508.08622

Momentum-Resolved Relaxation-Time Approach for Size-Dependent Conductivity in Anisotropic Metallic Films
Shrinking CMOS interconnect dimensions to the nanometer scale intensifies electron scattering at surfaces, interfaces, and grain boundaries, causing severe conductivity loss and challenging copper-based designs. Here we present a momentum-resolved relaxation time framework that integrates density functional theory with the semiclassical Boltzmann transport equation to predict size-dependent resistivity in metallic thin films. Electron phonon interactions are computed from first principles, and …

GENMANIP: LLM-driven Simulation for Generalizable Instruction-Following Manipulation
Ning Gao, Yilun Chen, Shuai Yang, Xinyi Chen, Yang Tian, Hao Li, Haifeng Huang, Hanqing Wang, Tai Wang, Jiangmiao Pang
https://arxiv.org/abs/2506.10966

GENMANIP: LLM-driven Simulation for Generalizable Instruction-Following Manipulation
Robotic manipulation in real-world settings remains challenging, especially regarding robust generalization. Existing simulation platforms lack sufficient support for exploring how policies adapt to varied instructions and scenarios. Thus, they lag behind the growing interest in instruction-following foundation models like LLMs, whose adaptability is crucial yet remains underexplored in fair comparisons. To bridge this gap, we introduce GenManip, a realistic tabletop simulation platform tailore…

VerIF: Verification Engineering for Reinforcement Learning in Instruction Following
Hao Peng, Yunjia Qi, Xiaozhi Wang, Bin Xu, Lei Hou, Juanzi Li
https://arxiv.org/abs/2506.09942 …

VerIF: Verification Engineering for Reinforcement Learning in Instruction Following
Reinforcement learning with verifiable rewards (RLVR) has become a key technique for enhancing large language models (LLMs), with verification engineering playing a central role. However, best practices for RL in instruction following remain underexplored. In this work, we explore the verification challenge in RL for instruction following and propose VerIF, a verification method that combines rule-based code verification with LLM-based verification from a large reasoning model (e.g., QwQ-32B). …

Adaptive Framework for Ambient Intelligence in Rehabilitation Assistance
G\'abor Baranyi, Zsolt Csibi, Kristian Fenech, \'Aron F\'othi, Zs\'ofia Ga\'al, Joul Skaf, Andr\'as L\H{o}rincz
https://arxiv.org/abs/2507.08624

Adaptive Framework for Ambient Intelligence in Rehabilitation Assistance
This paper introduces the Ambient Intelligence Rehabilitation Support (AIRS) framework, an advanced artificial intelligence-based solution tailored for home rehabilitation environments. AIRS integrates cutting-edge technologies, including Real-Time 3D Reconstruction (RT-3DR), intelligent navigation, and large Vision-Language Models (VLMs), to create a comprehensive system for machine-guided physical rehabilitation. The general AIRS framework is demonstrated in rehabilitation scenarios following…

Simulation of irradiated hybrid planar pixels modules at fluences expected at HL-LHC
Marco Bomben
https://arxiv.org/abs/2506.10823 https://

Simulation of irradiated hybrid planar pixels modules at fluences expected at HL-LHC
Signal loss is the main limitation on tracking/vertexing performance due to radiation damage effect to hybrid pixel detectors when irradiated at fluences expected at High Luminosity LHC (HL-LHC). It is important to have reliable predictions on the charge collection performance after irradiation in order to predict operational voltage values and test tracking algorithms robustness. In this paper the validation of combined TCAD and Monte Carlo simulations of hybrid silicon planar pixels sensors w…

G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration
Samuel Holt, Max Ruiz Luyten, Antonin Berthon, Mihaela van der Schaar
https://arxiv.org/abs/2506.09272

G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration
Constructing robust simulators is essential for asking "what if?" questions and guiding policy in critical domains like healthcare and logistics. However, existing methods often struggle, either failing to generalize beyond historical data or, when using Large Language Models (LLMs), suffering from inaccuracies and poor empirical alignment. We introduce G-Sim, a hybrid framework that automates simulator construction by synergizing LLM-driven structural design with rigorous empirical calibration…

AEGIS: Authenticity Evaluation Benchmark for AI-Generated Video Sequences
Jieyu Li, Xin Zhang, Joey Tianyi Zhou
https://arxiv.org/abs/2508.10771 https://ar…

AEGIS: Authenticity Evaluation Benchmark for AI-Generated Video Sequences
Recent advances in AI-generated content have fueled the rise of highly realistic synthetic videos, posing severe risks to societal trust and digital integrity. Existing benchmarks for video authenticity detection typically suffer from limited realism, insufficient scale, and inadequate complexity, failing to effectively evaluate modern vision-language models against sophisticated forgeries. To address this critical gap, we introduce AEGIS, a novel large-scale benchmark explicitly targeting the …