Tootfinder

Opt-in global Mastodon full text search. Join the index!

No exact results. Similar results found.
@arXiv_csAI_bot@mastoxiv.page
2025-06-18 08:04:15

Lightweight Relevance Grader in RAG
Taehee Jeong
arxiv.org/abs/2506.14084 arxiv.org/pdf/2506.14084

@arXiv_csRO_bot@mastoxiv.page
2025-07-17 07:55:40

A Roadmap for Climate-Relevant Robotics Research
Alan Papalia, Charles Dawson, Laurentiu L. Anton, Norhan Magdy Bayomi, Bianca Champenois, Jung-Hoon Cho, Levi Cai, Joseph DelPreto, Kristen Edwards, Bilha-Catherine Githinji, Cameron Hickert, Vindula Jayawardana, Matthew Kramer, Shreyaa Raghavan, David Russell, Shide Salimi, Jingnan Shi, Soumya Sudhakar, Yanwei Wang, Shouyi Wang, Luca Carlone, Vijay Kumar, Daniela Rus, John E. Fernandez, Cathy Wu, George Kantor, Derek Young, Hanumant Sin…

@heiseonline@social.heise.de
2025-09-12 03:06:00

Gmail-App separiert Käufe und Paketverfolgung, stellt relevante Werbung heraus
Google spendiert allen Nutzern von Gmail zwei neue Funktionen. Käufe und Paketzustellungen sind im Menü zu finden, Werbung wird nach Relevanz sortiert.

@ErikJonker@mastodon.social
2025-07-17 10:07:55

Echt goed nieuws, iedereen die de beschikking heeft over relevante Nederlandse content zou dat beschikbaar moeten stellen aan GPT-NL !
Doe mee met GPT-NL! - gpt-nl.nl/samenwerken/doe-mee/

@arXiv_csCL_bot@mastoxiv.page
2025-07-18 07:32:32

Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models
Lionel Wong, Katherine M. Collins, Lance Ying, Cedegao E. Zhang, Adrian Weller, Tobias Gersternberg, Timothy O'Donnell, Alexander K. Lew, Jacob D. Andreas, Joshua B. Tenenbaum, Tyler Brooke-Wilson
arxiv.org/abs/2507.12547

@arXiv_econEM_bot@mastoxiv.page
2025-09-17 07:40:29

Policy-relevant causal effect estimation using instrumental variables with interference
Didier Nibbering, Matthijs Oosterveen
arxiv.org/abs/2509.12538

@LillyHerself@Mastodon.social
2025-09-17 18:50:16

I ordered in a DVD of "Wag The Dog" because it's ages since I saw it, and I had the feeling it would feel relevant.
WHOA, so much more so than I had thought!
Worth a watch, or rewatch - highly recommend ⭐ ⭐⭐⭐⭐

DVD cover of Wag The Dog, showing Dustin Hoffman and Robert de Niro.
@digitalnaiv@mastodon.social
2025-09-17 06:23:00

Wer denkt, Austritt aus TikTok/X wäre Kapitulation, verkennt das Spiel: Die Plattformbetreiber brauchen unsere Aufmerksamkeit – nicht unseren Widerspruch. Kuketz rät: Relevanz entziehen, Alternativen stärken. Nur außerhalb der Empörungsmaschine wird wirkliche Opposition sichtbar. #socialmedia

@pbloem@sigmoid.social
2025-07-18 09:25:22

Now out in #TMLR:
🍇 GRAPES: Learning to Sample Graphs for Scalable Graph Neural Networks 🍇
There's lots of work on sampling subgraphs for GNNs, but relatively little on making this sampling process _adaptive_. That is, learning to select the data from the graph that is relevant for your task.
We introduce an RL-based and a GFLowNet-based sampler and show that the approach perf…

A diagram of the GRAPES pipeline. It shows a subgraph being sampled in two steps and being fed to a GNN, with a blue line showing the learning signal. The caption reads Figure 1: Overview of GRAPES. First, GRAPES processes a target node (green) by computing node inclusion probabilities on its 1-hop neighbors (shown by node color shade) with a sampling GNN. Given these probabilities, GRAPES samples k nodes. Then, GRAPES repeats this process over nodes in the 2-hop neighborhood. We pass the sampl…
A results table for node classification on heterophilious graphs. Table 2: F1-scores (%) for different sampling methods trained on heterophilous graphs for a batch size of 256, and a sample size of 256 per layer. We report the mean and standard deviation over 10 runs. The best values among the sampling baselines (all except GAS) are in bold, and the second best are underlined. MC stands for multi-class and ML stands for multi-label classification. OOM indicates out of memory.
Performance of samples vs sampling size showing that GRAPES generally performs well across sample sizes, while other samplers often show more variance across sample sizes. The caption reads Figure 4: Comparative analysis of classification accuracy across different sampling sizes for sampling baseline
and GRAPES. We repeated each experiment five times: The shaded regions show the 95% confidence intervals.
A diagrammatic illustration of a graph classification task used in one of the theorems. The caption reads Figure 9: An example of a graph for Theorem 1 with eight nodes. Red edges belong to E1, features xi and labels yi are shown beside every node. For nodes v1 and v2 we show the edge e12 as an example. As shown, the label of each node is the second feature of its neighbor, where a red edge connects them. The edge homophily ratio is h=12/28 = 0.43.
@arXiv_csRO_bot@mastoxiv.page
2025-06-18 09:17:10

ros2 fanuc interface: Design and Evaluation of a Fanuc CRX Hardware Interface in ROS2
Paolo Franceschi, Marco Faroni, Stefano Baraldo, Anna Valente
arxiv.org/abs/2506.14487