Tootfinder

Infini-gram mini: Exact n-gram Search at the Internet Scale with FM-Index
Hao Xu, Jiacheng Liu, Yejin Choi, Noah A. Smith, Hannaneh Hajishirzi
https://arxiv.org/abs/2506.12229

Infini-gram mini: Exact n-gram Search at the Internet Scale with FM-Index
Language models are trained mainly on massive text data from the Internet, and it becomes increasingly important to understand this data source. Exact-match search engines enable searching in large text corpora -- counting string appearances and retrieving the enclosing documents -- yet the high storage overhead hinders their application on Internet-scale data. We present Infini-gram mini, an efficient and scalable system that can make petabyte-level text corpora searchable. Based on the FM-ind…

Acting and Planning with Hierarchical Operational Models on a Mobile Robot: A Study with RAE UPOM
Oscar Lima, Marc Vinci, Sunandita Patra, Sebastian Stock, Joachim Hertzberg, Martin Atzmueller, Malik Ghallab, Dana Nau, Paolo Traverso
https://arxiv.org/abs/2507.11345

Acting and Planning with Hierarchical Operational Models on a Mobile Robot: A Study with RAE+UPOM
Robotic task execution faces challenges due to the inconsistency between symbolic planner models and the rich control structures actually running on the robot. In this paper, we present the first physical deployment of an integrated actor-planner system that shares hierarchical operational models for both acting and planning, interleaving the Reactive Acting Engine (RAE) with an anytime UCT-like Monte Carlo planner (UPOM). We implement RAE+UPOM on a mobile manipulator in a real-world deployment…

Despite what many purchasing departments think, software developers are not fungible assets.
https://www.linkedin.com/posts/alsutton_im

Unreal is all you need: Multimodal ISAC Data Simulation with Only One Engine
Kongwu Huang, Shiyi Mu, Jun Jiang, Yuan Gao, Shugong Xu
https://arxiv.org/abs/2507.08716

Unreal is all you need: Multimodal ISAC Data Simulation with Only One Engine
Scaling laws have achieved success in LLM and foundation models. To explore their potential in ISAC research, we propose Great-X. This single-engine multimodal data twin platform reconstructs the ray-tracing computation of Sionna within Unreal Engine and is deeply integrated with autonomous driving tools. This enables efficient and synchronized simulation of multimodal data, including CSI, RGB, Radar, and LiDAR. Based on this platform, we construct an open-source, large-scale, low-altitude UAV …

So to summarize this whole adventure:
1. A good 45 minutes was spent to get an answer that we probably could have gotten in 5 minutes in the 2010's, or in maybe 1-2 hours in the 1990's.
2. The time investment wasn't a total waste as we learned a lot along the way that we wouldn't have in the 2010's. Most relevant is the wide range of variation (e.g. a 2x factor depending on fiber intake!).
3. Most of the search engine results were confidently wrong answers that had no relation to reality. We were lucky to get one that had real citations we could start from (but that same article included the bogus 4.91 kcal/gram number). Next time I want to know a random factoid I might just start on Google scholar.
4. At least one page we chased citations through had a note at the top about being frozen due to NIH funding issues. The digital commons is under attack on multiple fronts.
All of this is yet another reason not to support the big LLM companies.
#AI

Simulation of surface x-ray emission from the ASTERICS ECR ion source
Thomas Thuillier, Andrea Cernuschi, Benjamin Cheymol
https://arxiv.org/abs/2507.06074

Simulation of surface x-ray emission from the ASTERICS ECR ion source
The bremsstrahlung x-ray emission induced by the impact of plasma electrons de-confined on the chamber wall of the ASTERICS electron cyclotron resonance ion source is investigated through a suite of two simulation codes. The electron high energy temperature distribution tail at the wall is found to be anisotropic and increases with Bmin. The electrons impinge the walls with broad angular distribution peaking at angles ranging between 5-25° with respect to the surface, which has consequences on…

The Variable Radio Emission of V830 Tau and Its Putative Planet
Rachel A. Osten, Scott J. Wolk
https://arxiv.org/abs/2509.05082 https://arxiv.org/pdf/2509.…

The Variable Radio Emission of V830 Tau and Its Putative Planet
We report on the first moderate-length time-scale observations of a young stellar object (YSO) at microwave frequencies. V830 Tau was monitored over the course of eight days with the JVLA at a frequency range of 4-8 GHz. Previous brief radio observations of this purported planet-hosting star indicated a radio-bright source with sparse evidence of dramatic intensity changes. Our observations confirm variability larger than a factor of five over the 8 days, with closer-spaced data indicating a lo…

AI-SearchPlanner: Modular Agentic Search via Pareto-Optimal Multi-Objective Reinforcement Learning
Lang Mei, Zhihan Yang, Chong Chen
https://arxiv.org/abs/2508.20368 https://

AI-SearchPlanner: Modular Agentic Search via Pareto-Optimal Multi-Objective Reinforcement Learning
Recent studies have explored integrating Large Language Models (LLMs) with search engines to leverage both the LLMs' internal pre-trained knowledge and external information. Specially, reinforcement learning (RL) has emerged as a promising paradigm for enhancing LLM reasoning through multi-turn interactions with search engines. However, existing RL-based search agents rely on a single LLM to handle both search planning and question-answering (QA) tasks in an end-to-end manner, which limits thei…

SERP Interference Network and Its Applications in Search Advertising
Purak Jain, Sandeep Appala
https://arxiv.org/abs/2506.21598 https://

SERP Interference Network and Its Applications in Search Advertising
Search Engine marketing teams in the e-commerce industry manage global search engine traffic to their websites with the aim to optimize long-term profitability by delivering the best possible customer experience on Search Engine Results Pages (SERPs). In order to do so, they need to run continuous and rapid Search Marketing A/B tests to continuously evolve and improve their products. However, unlike typical e-commerce A/B tests that can randomize based on customer identification, their tests fa…

TURA: Tool-Augmented Unified Retrieval Agent for AI Search
Zhejun Zhao, Yuehu Dong, Alley Liu, Lixue Zheng, Pingsheng Liu, Dongdong Shen, Long Xia, Jiashu Zhao, Dawei Yin
https://arxiv.org/abs/2508.04604

TURA: Tool-Augmented Unified Retrieval Agent for AI Search
The advent of Large Language Models (LLMs) is transforming search engines into conversational AI search products, primarily using Retrieval-Augmented Generation (RAG) on web corpora. However, this paradigm has significant industrial limitations. Traditional RAG approaches struggle with real-time needs and structured queries that require accessing dynamically generated content like ticket availability or inventory. Limited to indexing static pages, search engines cannot perform the interactive q…