Tootfinder

Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following
Minjong Yoo, Jinwoo Jang, Wei-jin Park, Honguk Woo
https://arxiv.org/abs/2509.08222 https:/…

Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following
This study presents an Exploratory Retrieval-Augmented Planning (ExRAP) framework, designed to tackle continual instruction following tasks of embodied agents in dynamic, non-stationary environments. The framework enhances Large Language Models' (LLMs) embodied reasoning capabilities by efficiently exploring the physical environment and establishing the environmental context memory, thereby effectively grounding the task planning process in time-varying environment contexts. In ExRAP, given mul…

Additive Approximation Schemes for Low-Dimensional Embeddings
Prashanti Anderson, Ainesh Bakshi, Samuel B. Hopkins
https://arxiv.org/abs/2509.09652 https://

Additive Approximation Schemes for Low-Dimensional Embeddings
We consider the task of fitting low-dimensional embeddings to high-dimensional data. In particular, we study the $k$-Euclidean Metric Violation problem ($\textsf{$k$-EMV}$), where the input is $D \in \mathbb{R}^{\binom{n}{2}}_{\geq 0}$ and the goal is to find the closest vector $X \in \mathbb{M}_{k}$, where $\mathbb{M}_k \subset \mathbb{R}^{\binom{n}{2}}_{\geq 0}$ is the set of all $k$-dimensional Euclidean metrics on $n$ points, and closeness is formulated as the following optimization problem…

Complex Logical Instruction Generation
Mian Zhang, Shujian Liu, Sixun Dong, Ming Yin, Yebowen Hu, Xun Wang, Steven Ma, Song Wang, Sathish Reddy Indurthi, Haoyun Deng, Zhiyu Zoey Chen, Kaiqiang Song
https://arxiv.org/abs/2508.09125

Complex Logical Instruction Generation
Instruction following has catalyzed the recent era of Large Language Models (LLMs) and is the foundational skill underpinning more advanced capabilities such as reasoning and agentic behaviors. As tasks grow more challenging, the logic structures embedded in natural language instructions becomes increasingly intricate. However, how well LLMs perform on such logic-rich instructions remains under-explored. We propose LogicIFGen and LogicIFEval. LogicIFGen is a scalable, automated framework for ge…

ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks
Kaijun Wang, Liqin Lu, Mingyu Liu, Jianuo Jiang, Zeju Li, Bolin Zhang, Wancai Zheng, Xinyi Yu, Hao Chen, Chunhua Shen
https://arxiv.org/abs/2508.08240

ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks
Language-guided long-horizon mobile manipulation has long been a grand challenge in embodied semantic reasoning, generalizable manipulation, and adaptive locomotion. Three fundamental limitations hinder progress: First, although large language models have improved spatial reasoning and task planning through semantic priors, existing implementations remain confined to tabletop scenarios, failing to address the constrained perception and limited actuation ranges of mobile platforms. Second, curre…

The Law-Following AI Framework: Legal Foundations and Technical Constraints. Legal Analogues for AI Actorship and technical feasibility of Law Alignment
Katalina Hernandez Delgado
https://arxiv.org/abs/2509.08009

The Law-Following AI Framework: Legal Foundations and Technical Constraints. Legal Analogues for AI Actorship and technical feasibility of Law Alignment
This paper critically evaluates the "Law-Following AI" (LFAI) framework proposed by O'Keefe et al. (2025), which seeks to embed legal compliance as a superordinate design objective for advanced AI agents and enable them to bear legal duties without acquiring the full rights of legal persons. Through comparative legal analysis, we identify current constructs of legal actors without full personhood, showing that the necessary infrastructure already exists. We then interrogate the framework's clai…

Hmmmm… here is a problem I did not anticipate.
Every time I empty the main pond hole of water, (the actual hole under the liner) water returns within an hour or two. I’ve done it 4 times now, and it keeps filling back up with water.
Obviously there is water underground infiltrating into the pond hole, and/or the water table itself is above the bottom of the hole. It is not coming from either of the other holes because they both have the same amount of water in them as they did this morning.
I have “watered” the blueberry patch and hazelnut tree a lot with the water that I have been cleaning the filter with… and we also had lots of water flying around outside the liners yesterday as I tested the pump. So it is quite possible that the ground around the pond is simply well saturated.
I think I am going to have to just keep removing the water (and putting it into the sewer) until it does not refill. We have a week of hot weather coming. Surely that will be enough time for everything to dry out completely.
Otherwise I might run into some issues if the rains return before I can anchor down the pond liner with gravel and get the plumbing in!
How is time already running short!?
Never underestimate the ability of water to find a place where it is not wanted. 😆
#poolpond #backyardProject #diy

Direct Measurement of Electron Heating in Electron-Only Reconnection in a Laboratory Mini-Magnetosphere
Lucas Rovige, Filipe D. Cruz, Timothy Van Hoomisen, Robert S. Dorst, Carmen G. Constantin, Stephen Vincena, Luis O. Silva, Christoph Niemann, Derek B. Schaeffer
https://arxiv.org/abs/2508.09086

Direct Measurement of Electron Heating in Electron-Only Reconnection in a Laboratory Mini-Magnetosphere
We report on the experimental observation of electron heating in electron-only magnetic reconnection in laser-driven laboratory mini-magnetospheres on the Large Plasma Device (LAPD) at the University of California, Los Angeles. In this experiment, a fast-flowing plasma impacts a pulsed magnetic dipole embedded within LAPD's magnetized ambient plasma, creating an ion-scale magnetosphere and driving electron-only magnetic reconnection between the background and dipole field lines. The electron ve…

Log2Sig: Frequency-Aware Insider Threat Detection via Multivariate Behavioral Signal Decomposition
Kaichuan Kong, Dongjie Liu, Xiaobo Jin, Zhiying Li, Guanggang Geng
https://arxiv.org/abs/2508.05696

Log2Sig: Frequency-Aware Insider Threat Detection via Multivariate Behavioral Signal Decomposition
Insider threat detection presents a significant challenge due to the deceptive nature of malicious behaviors, which often resemble legitimate user operations. However, existing approaches typically model system logs as flat event sequences, thereby failing to capture the inherent frequency dynamics and multiscale disturbance patterns embedded in user behavior. To address these limitations, we propose Log2Sig, a robust anomaly detection framework that transforms user logs into multivariate behav…

TrackVLA : Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking
Jiahang Liu, Yunpeng Qi, Jiazhao Zhang, Minghan Li, Shaoan Wang, Kui Wu, Hanjing Ye, Hong Zhang, Zhibo Chen, Fangwei Zhong, Zhizheng Zhang, He Wang
https://arxiv.org/abs/2510.07134

TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking
Embodied Visual Tracking (EVT) is a fundamental ability that underpins practical applications, such as companion robots, guidance robots and service assistants, where continuously following moving targets is essential. Recent advances have enabled language-guided tracking in complex and unstructured scenes. However, existing approaches lack explicit spatial reasoning and effective temporal memory, causing failures under severe occlusions or in the presence of similar-looking distractors. To add…

Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts
Rochana Prih Hastuti, Rian Adam Rajagede, Mansour Al Ghanim, Mengxin Zheng, Qian Lou
https://arxiv.org/abs/2509.07755 …

Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts
As large language models (LLMs) adapted to sensitive domains such as medicine, their fluency raises safety risks, particularly regarding provenance and accountability. Watermarking embeds detectable patterns to mitigate these risks, yet its reliability in medical contexts remains untested. Existing benchmarks focus on detection-quality tradeoffs, overlooking factual risks under low-entropy settings often exploited by watermarking's reweighting strategy. We propose a medical-focused evaluation w…