Tootfinder

Mixture of Raytraced Experts
Andrea Perin, Giacomo Lagomarsini, Claudio Gallicchio, Giuseppe Nuti
https://arxiv.org/abs/2507.12419 https://

Mixture of Raytraced Experts
We introduce a Mixture of Raytraced Experts, a stacked Mixture of Experts (MoE) architecture which can dynamically select sequences of experts, producing computational graphs of variable width and depth. Existing MoE architectures generally require a fixed amount of computation for a given sample. Our approach, in contrast, yields predictions with increasing accuracy as the computation cycles through the experts' sequence. We train our model by iteratively sampling from a set of candidate exper…

Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback
Janet Wang, Yunbei Zhang, Zhengming Ding, Jihun Hamm
https://arxiv.org/abs/2506.12323

Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback
Paucity of medical data severely limits the generalizability of diagnostic ML models, as the full spectrum of disease variability can not be represented by a small clinical dataset. To address this, diffusion models (DMs) have been considered as a promising avenue for synthetic image generation and augmentation. However, they frequently produce medically inaccurate images, deteriorating the model performance. Expert domain knowledge is critical for synthesizing images that correctly encode clin…

Beyond One-Size-Fits-All: A Study of Neural and Behavioural Variability Across Different Recommendation Categories
Georgios Koutroumpas, Sebastian Idesis, Mireia Masias Bruns, Carlos Segura, Joemon M. Jose, Sergi Abadal, Ioannis Arapakis
https://arxiv.org/abs/2506.13409

Beyond One-Size-Fits-All: A Study of Neural and Behavioural Variability Across Different Recommendation Categories
Traditionally, Recommender Systems (RS) have primarily measured performance based on the accuracy and relevance of their recommendations. However, this algorithmic-centric approach overlooks how different types of recommendations impact user engagement and shape the overall quality of experience. In this paper, we shift the focus to the user and address for the first time the challenge of decoding the neural and behavioural variability across distinct recommendation categories, considering more…

StacKAT: Infinite State Network Verification
Jules Jacobs, Nate Foster, Tobias Kapp\'e, Dexter Kozen, Lily Saada, Alexandra Silva, Jana Wagemaker
https://arxiv.org/abs/2506.13383

StacKAT: Infinite State Network Verification
We develop StacKAT, a network verification language featuring loops, finite state variables, nondeterminism, and - most importantly - access to a stack with accompanying push and pop operations. By viewing the variables and stack as the (parsed) headers and (to-be-parsed) contents of a network packet, StacKAT can express a wide range of network behaviors including parsing, source routing, and telemetry. These behaviors are difficult or impossible to model using existing languages like NetKAT. W…

Astro-MoE: Mixture of Experts for Multiband Astronomical Time Series
Martina C\'adiz-Leyton, Guillermo Cabrera-Vives, Pavlos Protopapas, Daniel Moreno-Cartagena, Ignacio Becker
https://arxiv.org/abs/2507.12611

Astro-MoE: Mixture of Experts for Multiband Astronomical Time Series
Multiband astronomical time series exhibit heterogeneous variability patterns, sampling cadences, and signal characteristics across bands. Standard transformers apply shared parameters to all bands, potentially limiting their ability to model this rich structure. In this work, we introduce Astro-MoE, a foundational transformer architecture that enables dynamic processing via a Mixture of Experts module. We validate our model on both simulated (ELAsTiCC-1) and real-world datasets (Pan-STARRS1).

Detecting In-Person Conversations in Noisy Real-World Environments with Smartwatch Audio and Motion Sensing
Alice Zhang, Callihan Bertley, Dawei Liang, Edison Thomaz
https://arxiv.org/abs/2507.12002

Detecting In-Person Conversations in Noisy Real-World Environments with Smartwatch Audio and Motion Sensing
Social interactions play a crucial role in shaping human behavior, relationships, and societies. It encompasses various forms of communication, such as verbal conversation, non-verbal gestures, facial expressions, and body language. In this work, we develop a novel computational approach to detect a foundational aspect of human social interactions, in-person verbal conversations, by leveraging audio and inertial data captured with a commodity smartwatch in acoustically-challenging scenarios. To…

FEWSim: A Visual Analytic Framework for Exploring the Nexus of Food-Energy-Water Simulations
Fan Lei, David A. Sampson, Jiayi Hong, Yuxin Ma, Giuseppe Mascaro, Dave White, Rimjhim Agarwal, Ross Maciejewski
https://arxiv.org/abs/2506.14056

FEWSim: A Visual Analytic Framework for Exploring the Nexus of Food-Energy-Water Simulations
The interdependencies of food, energy, and water (FEW) systems create a nexus opportunity to explore the strengths and vulnerabilities of individual and cross-sector interactions within FEW systems. However, the variables quantifying nexus interactions are hard to observe, which hinders the cross-sector analysis. To overcome such challenges, we present FEWSim, a visual analytics framework designed to support domain experts in exploring and interpreting simulation results from a coupled FEW mode…

Contemporary AI foundation models increase biological weapons risk
Roger Brent, T. Greg McKelvey Jr
https://arxiv.org/abs/2506.13798 https://

Contemporary AI foundation models increase biological weapons risk
The rapid advancement of artificial intelligence has raised concerns about its potential to facilitate biological weapons development. We argue existing safety assessments of contemporary foundation AI models underestimate this risk, largely due to flawed assumptions and inadequate evaluation methods. First, assessments mistakenly assume biological weapons development requires tacit knowledge, or skills gained through hands-on experience that cannot be easily verbalized. Second, they rely on im…

Serving Large Language Models on Huawei CloudMatrix384
Pengfei Zuo, Huimin Lin, Junbo Deng, Nan Zou, Xingkun Yang, Yingyu Diao, Weifeng Gao, Ke Xu, Zhangyu Chen, Shirui Lu, Zhao Qiu, Peiyang Li, Xianyu Chang, Zhengzhong Yu, Fangzheng Miao, Jia Zheng, Ying Li, Yuan Feng, Bei Wang, Zaijian Zong, Mosong Zhou, Wenli Zhou, Houjiang Chen, Xingyu Liao, Yipeng Li, Wenxiao Zhang, Ping Zhu, Yinggang Wang, Chuanjie Xiao, Depeng Liang, Dong Cao, Juncheng Liu, Yongqiang Yang, Xiaolong Bai, Yi Li, H…

Serving Large Language Models on Huawei CloudMatrix384
The rapid evolution of large language models (LLMs), driven by growing parameter scales, adoption of mixture-of-experts (MoE) architectures, and expanding context lengths, imposes unprecedented demands on AI infrastructure. Traditional AI clusters face limitations in compute intensity, memory bandwidth, inter-chip communication, and latency, compounded by variable workloads and strict service-level objectives. Addressing these issues requires fundamentally redesigned hardware-software integrati…

On QoE-Aware Traffic Management for Real-time, Interactive Video with Time-variant Spatial Complexity
Szilveszter N\'adas, Lars Ernstr\"om, David Lindero, Jonathan Lynam
https://arxiv.org/abs/2507.11798

On QoE-Aware Traffic Management for Real-time, Interactive Video with Time-variant Spatial Complexity
We analyzed spatial complexity, defined as the relationship between the required bitrate and a corresponding picture Quality of Experience (QoE) metric, for realistic, long, real-time, interactive video clips. Apart from variation across different content types, e.g., game genres, we discovered time-variability within a clip from second to second, and explored the ramifications for traffic management. We introduced utility as an elegant way to manage resource sharing preferences. Our analysis o…