Tootfinder

FLOWING: Implicit Neural Flows for Structure-Preserving Morphing
Arthur Bizzi, Matias Grynberg, Vitor Matias, Daniel Perazzo, Jo\~ao Paulo Lima, Luiz Velho, Nuno Gon\c{c}alves, Jo\~ao Pereira, Guilherme Schardong, Tiago Novello
https://arxiv.org/abs/2510.09537

FLOWING: Implicit Neural Flows for Structure-Preserving Morphing
Morphing is a long-standing problem in vision and computer graphics, requiring a time-dependent warping for feature alignment and a blending for smooth interpolation. Recently, multilayer perceptrons (MLPs) have been explored as implicit neural representations (INRs) for modeling such deformations, due to their meshlessness and differentiability; however, extracting coherent and accurate morphings from standard MLPs typically relies on costly regularizations, which often lead to unstable traini…

Moody Urbanity - UP 🔝
情绪化城市 - 上面 🔝
📷 Nikon FE
🎞️ Ilford HP5 Plus 400, expired 1993
#filmphotography #Photography #blackandwhite

Interesting thread to get a first-hand account on the current state of LLMs for assisting US tax filings, even in complex situations. tl;dr: Very helpful for a sophisticated user that can check the output.
Another point towards my very narrow defense of LLMs, i.e., feel free to dislike LLMs for many good reasons, but please don't call them useless.

Patrick McKenzie
So October 15th, the extended US tax deadline, is just around the corner, and I have some observations which are more about LLM progress than taxes. Background: many people professionally involved with LLMs estimate 2026-2028 as the year where one can get an LLM to "do taxes."

Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
Miao Lu, Weiwei Sun, Weihua Du, Zhan Ling, Xuesong Yao, Kang Liu, Jiecao Chen
https://arxiv.org/abs/2510.06727

Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
We study reinforcement learning (RL) fine-tuning of large language model (LLM) agents for long-horizon multi-turn tool use, where context length quickly becomes a fundamental bottleneck. Existing RL pipelines can suffer from degraded instruction following, excessive rollout costs, and most importantly, strict context limits. To address these challenges, we introduce summarization-based context management to training. In specific, it periodically compresses the tool using history by LLM-generate…

Superconducting meander-line surface coil for NMR spectroscopy of nanoscale thin films
Louis Beaudoin, Aim\'e Verrier, Youcef A. Bioud, Mathieu Massicotte, Bertrand Reulet, Jeffrey A. Quilliam
https://arxiv.org/abs/2510.07679

Superconducting meander-line surface coil for NMR spectroscopy of nanoscale thin films
Nuclear magnetic resonance (NMR) spectroscopy is a powerful technique to study local magnetism in a variety of materials. However, the inherently low sensitivity of conventional inductively detected solid state NMR typically requires a large number of spins, reducing its applicability to two-dimensional (2D) materials and nanoscale thin films. To overcome this experimental challenge, we introduce a novel probe based on a superconducting meander-line surface coil that significantly enhances the …

NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents
Tianshi Zheng, Kelvin Kiu-Wai Tam, Newt Hue-Nam K. Nguyen, Baixuan Xu, Zhaowei Wang, Jiayang Cheng, Hong Ting Tsang, Weiqi Wang, Jiaxin Bai, Tianqing Fang, Yangqiu Song, Ginny Y. Wong, Simon See
https://arxiv.org/abs/2510.07172

NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents
Large language models are emerging as powerful tools for scientific law discovery, a foundational challenge in AI-driven science. However, existing benchmarks for this task suffer from a fundamental methodological trilemma, forcing a trade-off between scientific relevance, scalability, and resistance to memorization. Furthermore, they oversimplify discovery as static function fitting, failing to capture the authentic scientific process of uncovering embedded laws through the interactive explora…

Moody Urbanity - Relations V 🪢
情绪化城市 - 关系 V 🪢
📷 Minolta Hi-Matic AF
🎞️ Shanghai GP3 400 Pan
#filmphotography #Photography #blackandwhite

Mind the Gap: Linguistic Divergence and Adaptation Strategies in Human-LLM Assistant vs. Human-Human Interactions
Fulei Zhang, Zhou Yu
https://arxiv.org/abs/2510.02645 https://

Mind the Gap: Linguistic Divergence and Adaptation Strategies in Human-LLM Assistant vs. Human-Human Interactions
As Large Language Models (LLMs) are increasingly deployed in customer-facing applications, a critical yet underexplored question is how users communicate differently with LLM chatbots compared to human agent. In this study, we present empirical evidence that users adopt distinct communication styles when users interact with chatbots versus human agents. Our analysis reveals significant differences in grammatical fluency, politeness, and lexical diversity in user language between the two setting…

Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers
Gangwei Xu, Haotong Lin, Hongcheng Luo, Xianqi Wang, Jingfeng Yao, Lianghui Zhu, Yuechuan Pu, Cheng Chi, Haiyang Sun, Bing Wang, Guang Chen, Hangjun Ye, Sida Peng, Xin Yang
https://arxiv.org/abs/2510.07316

Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers
This paper presents Pixel-Perfect Depth, a monocular depth estimation model based on pixel-space diffusion generation that produces high-quality, flying-pixel-free point clouds from estimated depth maps. Current generative depth estimation models fine-tune Stable Diffusion and achieve impressive performance. However, they require a VAE to compress depth maps into latent space, which inevitably introduces \textit{flying pixels} at edges and details. Our model addresses this challenge by directly…

Read the Room: Inferring Social Context Through Dyadic Interaction Recognition in Cyber-physical-social Infrastructure Systems
Cheyu Lin, John Martins, Katherine A. Flanigan, Ph. D
https://arxiv.org/abs/2510.04854

Read the Room: Inferring Social Context Through Dyadic Interaction Recognition in Cyber-physical-social Infrastructure Systems
Cyber-physical systems (CPS) integrate sensing, computing, and control to improve infrastructure performance, focusing on economic goals like performance and safety. However, they often neglect potential human-centered (or ''social'') benefits. Cyber-physical-social infrastructure systems (CPSIS) aim to address this by aligning CPS with social objectives. This involves defining social benefits, understanding human interactions with each other and infrastructure, developing privacy-preserving me…