Tootfinder

About Our Greenish Home aka 16WW, with Bonus Bats and Sparrows - Learn more about our council-house turned SuperHome, that this site is based on! #podcast #greenLiving -

About Our Greenish Home aka 16WW, with Bonus Bats and Sparrows
Learn more about our council-house turned SuperHome, that this site is based on! #podcast #greenLiving

Here's something new. Our train is delayed because the #PKP #InterCity train going in front of us is delayed. And apparently that train is delayed because the conductor decided to remove a passenger over him keeping his shoes against the seat opposite him.
And the real absurd part is that apparently said passenger removed the shoes upon being called on it. Yet the conductor decided to call the police to forcibly remove him anyway. On a single track line known to be filled with trains to the capacity. Causing series of delays for hours to come. With a bunch of connections on all major nodes that will cause further delays.
#rail

MLLM-Driven Semantic Identifier Generation for Generative Cross-Modal Retrieval
Tianyuan Li, Lei Wang, Ahtamjan Ahmat, Yating Yang, Bo Ma, Rui Dong, Bangju Han
https://arxiv.org/abs/2509.17359

MLLM-Driven Semantic Identifier Generation for Generative Cross-Modal Retrieval
Generative cross-modal retrieval, which treats retrieval as a generation task, has emerged as a promising direction with the rise of Multimodal Large Language Models (MLLMs). In this setting, the model responds to a text query by generating an identifier corresponding to the target image. However, existing methods typically rely on manually crafted string IDs, clustering-based labels, or atomic identifiers requiring vocabulary expansion, all of which face challenges in semantic alignment or sca…

About Our Greenish Home aka 16WW, with Bonus Bats and Sparrows - Learn more about our council-house turned SuperHome, that this site is based on! #podcast #greenLiving -

About Our Greenish Home aka 16WW, with Bonus Bats and Sparrows
Learn more about our council-house turned SuperHome, that this site is based on! #podcast #greenLiving

When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models
Cheng Wang, Gelei Deng, Xianglin Yang, Han Qiu, Tianwei Zhang
https://arxiv.org/abs/2508.15407 h…

When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models
Large Audio-Language Models (LALMs) are enhanced with audio perception capabilities, enabling them to effectively process and understand multimodal inputs that combine audio and text. However, their performance in handling conflicting information between audio and text modalities remains largely unexamined. This paper introduces MCR-BENCH, the first comprehensive benchmark specifically designed to evaluate how LALMs prioritize information when presented with inconsistent audio-text pairs. Throu…

🥳 New Kitten Release
Housekeeping:
• Updated runtime version to Node version 22.18.0 (latest LTS).
• Removed `--experimental-global-customevent` in node launch command (as `CustomEvent` is no longer behing the CLI flag since Node v19.0.0)
• Renamed `--experimental-loader` flag to `--loader` as the experimental prefix is no longer required.
…

Frequentist Cosmological Constraints from Full-Shape Clustering Measurements in DESI DR1
James Morawetz, Hanyu Zhang, Marco Bonici, Will Percival, Andrea Crespi, Jessica Nicole Aguilar, Steven Ahlen, Davide Bianchi, David Brooks, Francisco Javier Castander, Todd Claybaugh, Shaun Cole, Andrei Cuceu, Axel de la Macorra, Arnaud de Mattia, Biprateep Dey, Peter Doel, Simone Ferraro, Andreu Font-Ribera, Jaime E. Forero-Romero, Enrique Gazta\~naga, Satya Gontcho A Gontcho, Gaston Gutierrez, C…

Frequentist Cosmological Constraints from Full-Shape Clustering Measurements in DESI DR1
We perform a frequentist analysis using the standard profile likelihood method for clustering measurements from Data Release 1 of the Dark Energy Spectroscopic Instrument (DESI). While Bayesian inferences for Effective Field Theory models of galaxy clustering can be highly sensitive to the choice of priors for extended cosmological models, frequentist inferences are not susceptible to such effects. We compare Bayesian and frequentist constraints for the parameter set $\{σ_8, H_0, Ω_{\rm{m}}, …

Mamdani was out in Forest Hills yesterday. My sister-in-law and a bunch of other folks got to see him, but I didn't get to (venue was full).
Meanwhile Grace Meng showed up to our shindig yesterday, which was cool, but I still would've rather had Mamdani!