@Techmeme@techhub.social2025-07-12 05:50:53
Analysis: YC picked just four Indian startups in 2024 vs. 66 in 2021, amid a growing trend of startups shifting their parent entities to India for domestic IPOs (The Economic Times)
https://economictimes.…
@arXiv_astrophGA_bot@mastoxiv.page2025-07-11 08:49:31
Orientation of galaxy spins relative to filaments of the large-scale structure of the Universe
A. V. Antipova, D. I. Makarov, N. Libeskind, E. Tempel
https://arxiv.org/abs/2507.07334
@arXiv_csCY_bot@mastoxiv.page2025-07-10 09:18:31
Exploring Public Perceptions of Generative AI in Libraries: A Social Media Analysis of X Discussions
Yuan Li, Teja Mandaloju, Haihua Chen
https://arxiv.org/abs/2507.07047
@arXiv_csAI_bot@mastoxiv.page2025-07-11 09:52:31
An Integrated Framework of Prompt Engineering and Multidimensional Knowledge Graphs for Legal Dispute Analysis
Mingda Zhang, Na Zhao, Jianglong Qing, Qing xu, Kaiwen Pan, Ting luo
https://arxiv.org/abs/2507.07893
@arXiv_csLG_bot@mastoxiv.page2025-07-11 10:23:51
Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs
Ziyue Li, Yang Li, Tianyi Zhou
https://arxiv.org/abs/2507.07996 https://arxiv.org/pdf/2507.07996 https://arxiv.org/html/2507.07996
arXiv:2507.07996v1 Announce Type: new
Abstract: Can a pretrained neural network adapt its architecture to different inputs without any finetuning? Do we need all layers for simple tasks, and are they adequate for challenging tasks? We found that the layers of a pretrained large language model (LLM) can be manipulated as separate modules to build a better and even shallower model customized for each test sample. In particular, each layer from the pretrained model can be skipped/pruned or repeated multiple times as recurrent neural networks (RNN), and stacked with others in arbitrary orders, yielding a chain-of-layers (CoLa) per sample. This compositional space greatly expands the scope of existing works on looped/recurrent pretrained modules, layer pruning, or early-exit networks. We develop a Monte Carlo Tree Search (MCTS) protocol to explore and identify the optimal CoLa for each sample from math and commonsense reasoning benchmarks. Compared to a static model of a fixed depth, CoLa allows shortcut paths (fast thinking), recurrence of the same layer(s) (slow thinking), and combining both, offering more flexible, dynamic architectures for different inputs. We conduct an extensive analysis of the MCTS-optimized CoLa, which leads to two key findings: (1) For >75% of samples with correct predictions by the original LLM, we can find shorter CoLa, suggesting a large space for improving inference efficiency; (2) For >60% of samples with originally incorrect predictions, we can identify CoLa achieving correct predictions, suggesting a large space of performance enhancement. Our results highlight the shortcomings of using a fixed architecture of pre-trained LLMs for inference on different samples and pave the way to unlock the generalization power of test-time depth adaptation.
toXiv_bot_toot
@arXiv_mathAP_bot@mastoxiv.page2025-07-10 09:10:51
Analysis of Reaction-Diffusion Predator-Prey System under Random Switching
Nguyen H. Du, Nhu N. Nguyen
https://arxiv.org/abs/2507.06491 https://arxiv.org/pdf/2507.06491 https://arxiv.org/html/2507.06491
arXiv:2507.06491v1 Announce Type: new
Abstract: This paper investigates the long-term dynamics of a reaction-diffusion predator-prey system subject to random environmental fluctuations modeled by Markovian switching. The model is formulated as a hybrid system of partial differential equations (PDEs), where the switching between different ecological regimes captures the randomness in environmental conditions. We derive a critical threshold parameter that determines whether the predator species will eventually go extinct or persist. We further characterize the system's asymptotic behavior by providing a detailed pathwise description of the omega-limit set of solutions. This analysis reveals how the effects of random switching shape the distribution and long-term coexistence of the species. Numerical simulations are provided to validate and illustrate the theoretical findings, highlighting transitions between different dynamical regimes. To the best of our knowledge, this is the first work that rigorously analyzes a spatially diffusive predator-prey model under Markovian switching, thereby bridging the gap between spatial ecology and stochastic hybrid PDE systems.
toXiv_bot_toot
@arXiv_condmatsoft_bot@mastoxiv.page2025-07-11 09:30:31
The effect of fiber plasticity on domain formation in soft biological composites -- Part I: a bifurcation analysis
Michalis Agoras, Fernanda F. Fontenele, Nikolaos Bouklas
https://arxiv.org/abs/2507.07843
@arXiv_csDS_bot@mastoxiv.page2025-07-11 08:58:31
Efficient and Adaptive Estimation of Local Triadic Coefficients
Ilie Sarpe, Aristides Gionis
https://arxiv.org/abs/2507.07536 https://
@arXiv_qfinST_bot@mastoxiv.page2025-06-10 10:23:52
Towards Competent AI for Fundamental Analysis in Finance: A Benchmark Dataset and Evaluation
Zonghan Wu, Junlin Wang, Congyuan Zou, Chenhan Wang, Yilei Shao
https://arxiv.org/abs/2506.07315
@arXiv_csHC_bot@mastoxiv.page2025-07-11 08:10:01
Pluri-perspectivism in Human-robot Co-creativity with Older Adults
Marianne Bossema, Rob Saunders, Aske Plaat, Somaya Ben Allouch
https://arxiv.org/abs/2507.07550
