Tootfinder

DIME-Net: A Dual-Illumination Adaptive Enhancement Network Based on Retinex and Mixture-of-Experts
Ziang Wang, Xiaoqin Wang, Dingyi Wang, Qiang Li, Shushan Qiao
https://arxiv.org/abs/2508.13921

DIME-Net: A Dual-Illumination Adaptive Enhancement Network Based on Retinex and Mixture-of-Experts
Image degradation caused by complex lighting conditions such as low-light and backlit scenarios is commonly encountered in real-world environments, significantly affecting image quality and downstream vision tasks. Most existing methods focus on a single type of illumination degradation and lack the ability to handle diverse lighting conditions in a unified manner. To address this issue, we propose a dual-illumination enhancement framework called DIME-Net. The core of our method is a Mixture-of…

EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence
Chaoyin She, Ruifang Lu, Lida Chen, Wei Wang, Qinghua Huang
https://arxiv.org/abs/2509.14977

EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence
Ultrasound imaging has become the preferred imaging modality for early cancer screening due to its advantages of non-ionizing radiation, low cost, and real-time imaging capabilities. However, conventional ultrasound diagnosis heavily relies on physician expertise, presenting challenges of high subjectivity and low diagnostic efficiency. Vision-language models (VLMs) offer promising solutions for this issue, but existing general-purpose models demonstrate limited knowledge in ultrasound medical …

MixCache: Mixture-of-Cache for Video Diffusion Transformer Acceleration
Yuanxin Wei, Lansong Diao, Bujiao Chen, Shenggan Cheng, Zhengping Qian, Wenyuan Yu, Nong Xiao, Wei Lin, Jiangsu Du
https://arxiv.org/abs/2508.12691

MixCache: Mixture-of-Cache for Video Diffusion Transformer Acceleration
Leveraging the Transformer architecture and the diffusion process, video DiT models have emerged as a dominant approach for high-quality video generation. However, their multi-step iterative denoising process incurs high computational cost and inference latency. Caching, a widely adopted optimization method in DiT models, leverages the redundancy in the diffusion process to skip computations in different granularities (e.g., step, cfg, block). Nevertheless, existing caching methods are limited …

NavMoE: Hybrid Model- and Learning-based Traversability Estimation for Local Navigation via Mixture of Experts
Botao He, Amir Hossein Shahidzadeh, Yu Chen, Jiayi Wu, Tianrui Guan, Guofei Chen, Howie Choset, Dinesh Manocha, Glen Chou, Cornelia Fermuller, Yiannis Aloimonos
https://arxiv.org/abs/2509.12747

NavMoE: Hybrid Model- and Learning-based Traversability Estimation for Local Navigation via Mixture of Experts
This paper explores traversability estimation for robot navigation. A key bottleneck in traversability estimation lies in efficiently achieving reliable and robust predictions while accurately encoding both geometric and semantic information across diverse environments. We introduce Navigation via Mixture of Experts (NAVMOE), a hierarchical and modular approach for traversability estimation and local navigation. NAVMOE combines multiple specialized models for specific terrain types, each of whi…

Fascinating:
A feature in the Financial Times reveals some very rich people have started selling up and living in motorhomes.
Obviously, they’re ultra-luxurious motorhomes. The owner of a private equity firm interviewed has a 30-tonne behemoth with air conditioning and high-speed internet, a kitchen, dining room, two bathrooms, a “spacious master bedroom” and “a range of modern hi-tech appliances”. which cost
“around $2.7m” (£2m)
I read something else about ultra-high…

Series D, Episode 07 - Assassin
BENOS: One moment, gentlemen. A late addition. Perhaps you'd like to send back a few details to your clients, especially the ladies. Now I know he looks soft, and he talks soft, too, but you can tell the ladies he's strong enough to work all day and still have plenty of energy left over for any little chores you might have for him in the evenings. [laughter] Now, what am I bid?
TOK: Valeria of Prim bids a hundred... [1/2] B7B5

Quantum vs Classical Thermal Transport at Low Temperatures
Zhixing Zou, Jiangbin Gong, Jiao Wang, Giulio Casati, Giuliano Benenti
https://arxiv.org/abs/2509.14027 https://

Quantum vs Classical Thermal Transport at Low Temperatures
This work aims to understand how quantum mechanics affects heat transport at low temperatures. In the classical setting, by considering a simple paradigmatic model, our simulations reveal the emergence of Negative Differential Thermal Resistance (NDTR): paradoxically, increasing the temperature bias by lowering the cold bath temperature reduces the steady-state heat current. In sharp contrast, the quantum version of the model, treated via a Lindblad master equation, exhibits no NDTR: the heat c…

Parity violation in framework of nonmetricity gravity
Zhiyuan Yu, Zhengsheng Yang, Taotao Qiu
https://arxiv.org/abs/2508.10532 https://arxiv.org/pdf/2508.1…

Parity violation in framework of nonmetricity gravity
The latest observational data of Planck satellite shows nontrivial value of polarization rotation angle caused by cosmic birefringence in the early universe. Moreover, the asymmetry of baryons versus anti-baryons still remains mysterious. Both of them indicates that there should be hidden new physics such as fundamental symmetry breaking. In this paper, we try to interpret these two events in framework of nonmetricity modified gravity. We introduce an interaction term between nonmetricity-based…

SSD Offloading for LLM Mixture-of-Experts Weights Considered Harmful in Energy Efficiency
Kwanhee Kyung, Sungmin Yun, Jung Ho Ahn
https://arxiv.org/abs/2508.06978 https://

SSD Offloading for LLM Mixture-of-Experts Weights Considered Harmful in Energy Efficiency
Large Language Models (LLMs) applying Mixture-of-Experts (MoE) scale to trillions of parameters but require vast memory, motivating a line of research to offload expert weights from fast-but-small DRAM (HBM) to denser Flash SSDs. While SSDs provide cost-effective capacity, their read energy per bit is substantially higher than that of DRAM. This paper quantitatively analyzes the energy implications of offloading MoE expert weights to SSDs during the critical decode stage of LLM inference. Our a…

Synthetic Protein-Ligand Complex Generation for Deep Molecular Docking
Sofiene Khiari, Matthew R. Masters, Amr H. Mahmoud, Markus A. Lill
https://arxiv.org/abs/2509.12915 https:…

Synthetic Protein-Ligand Complex Generation for Deep Molecular Docking
The scarcity of experimental protein-ligand complexes poses a significant challenge for training robust deep learning models for molecular docking. Given the prohibitive cost and time constraints associated with experimental structure determination, scalable generation of realistic protein-ligand complexes is needed to expand available datasets for model development. In this study, we introduce a novel workflow for the procedural generation and validation of synthetic protein-ligand complexes, …