Tootfinder

LLMC : Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkit
Chengtao Lv, Bilang Zhang, Yang Yong, Ruihao Gong, Yushi Huang, Shiqiao Gu, Jiajun Wu, Yumeng Shi, Jinyang Guo, Wenya Wang
https://arxiv.org/abs/2508.09981

LLMC+: Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkit
Large Vision-Language Models (VLMs) exhibit impressive multi-modal capabilities but suffer from prohibitive computational and memory demands, due to their long visual token sequences and massive parameter sizes. To address these issues, recent works have proposed training-free compression methods. However, existing efforts often suffer from three major limitations: (1) Current approaches do not decompose techniques into comparable modules, hindering fair evaluation across spatial and temporal r…

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[4/8]:
- D-CoDe: Scaling Image-Pretrained VLMs to Video via Dynamic Compression and Question Decomposition
Yiyang Huang, Yizhou Wang, Yun Fu

Series A, Episode 02 - Space Fall
LEYLAN: Yes.
BLAKE: These are mine. You will hand over all your weapons to my men. Whilst we hold the computer, the ship is helpless. It will remain that way until you agree. You will then fly this ship to the nearest habitable planet where the prisoners will disembark. Any attempt by your men to break into this room and we'll destroy the computer. Totally. That's all.

First-principles study of formic acid decomposition on single Pt atoms supported on heteroatom-doped graphene
Kazuma Sato, Norihito Sakaguchi, Yuji Kunisada
https://arxiv.org/abs/2509.07494

First-principles study of formic acid decomposition on single Pt atoms supported on heteroatom-doped graphene
Formic acid is a promising liquid hydrogen carrier, but its catalytic decomposition requires both high activity and selectivity toward dehydrogenation. Here, we investigated the catalytic activity and selectivity of formic acid decomposition on single Pt atoms supported on pristine and heteroatom-doped graphene using first-principles calculations based on the density functional theory. Reaction energy profiles reveal that single Pt atoms on P- and O-doped graphene show catalytic activity compar…

Kallen-Lehmann representation for Spinor-Scalar Loops in de Sitter Space-time. Spectral equations
Boris L. Altshuler
https://arxiv.org/abs/2508.07467 https://

Kallen-Lehmann representation for Spinor-Scalar Loops in de Sitter Space-time. Spectral equations
Compact formulas (1), (28) presented in this paper permit to formulate the Kallen-Lehmann harmonic decompositions of the products of two spinor and of spinor and scalar harmonic functions in AdS and Wightman functions in dS spaces; the correct flat space limit of the corresponding Kallen-Lehmann densities is demonstrated. Also in Sec. 4 the relatively simple, suitable for calculations Kallen-Lehmann representations of the real parts of spinor and scalar one-loop self-energies in Yukawa model in…

Sparse domination via the Calder\'on-Zygmund decomposition: the example of Dini-smooth kernels
Fernando Ballesta-Yag\"ue, Jos\'e M. Conde-Alonso
https://arxiv.org/abs/2509.07659

Sparse domination via the Calderón-Zygmund decomposition: the example of Dini-smooth kernels
In this expository article, we briefly survey the main known schemes of proof of sparse domination principles within harmonic analysis. We then use the one based on the Calderón-Zygmund decomposition to prove a dual sparse domination estimate for Calderón-Zymgund operators with Dini-smooth kernels, with an eye on the difficulties that arise when trying to transfer the argument to spaces with nondoubling measures.

WebDART: Dynamic Decomposition and Re-planning for Complex Web Tasks
Jingbo Yang, Bairu Hou, Wei Wei, Shiyu Chang, Yujia Bao
https://arxiv.org/abs/2510.06587 https://

WebDART: Dynamic Decomposition and Re-planning for Complex Web Tasks
Large language model (LLM) agents are becoming competent at straightforward web tasks, such as opening an item page or submitting a form, but still struggle with objectives that require long horizon navigation, large scale information extraction, and reasoning under constraints. We present WebDART, a general framework that enables a single LLM to handle such complex chores. WebDART (i) dynamically decomposes each objective into three focused subtasks: navigation, information extraction, and exe…

This is the time to speak out, to disembed our selves from a fascist system, to place principles over profit and self-advancement.
To be what Viet Thanh Nguyen calls “disagreeable”.
Yes, of course there are risks.
But at this moment, with ICE in the streets and at our door,
when each hour another liberty is being erased,
and those who speak truth to power are being removed from TV,
from universities, from cultural centers,
when the cultural platform…

Strong rumours of an end-of-cycle pattern club algorave at Sidney Matilda Sheffield on sun 14th December 2025

Hit them where it hurts.
#DisneyPlus #JimmyKimmel