Tootfinder

CETUS: Causal Event-Driven Temporal Modeling With Unified Variable-Rate Scheduling
Hanfang Liang, Bing Wang, Shizhen Zhang, Wen Jiang, Yizhuo Yang, Weixiang Guo, Shenghai Yuan
https://arxiv.org/abs/2509.13784

CETUS: Causal Event-Driven Temporal Modeling With Unified Variable-Rate Scheduling
Event cameras capture asynchronous pixel-level brightness changes with microsecond temporal resolution, offering unique advantages for high-speed vision tasks. Existing methods often convert event streams into intermediate representations such as frames, voxel grids, or point clouds, which inevitably require predefined time windows and thus introduce window latency. Meanwhile, pointwise detection methods face computational challenges that prevent real-time efficiency due to their high computati…

Replaced article(s) found for econ.TH. https://arxiv.org/list/econ.TH/new
[1/1]:
- The equilibrium properties of obvious strategy profiles in games with many players
Enxian Chen Bin Wu Hanping Xu

I don't fundamentally hate AI transcription, especially where the alternative is nothing, but seeing it mis-guess homophones (in a way that a human that understands the context wouldn't), while providing no way to report back errors, is maddening.

PAC: Pronunciation-Aware Contextualized Large Language Model-based Automatic Speech Recognition
Li Fu, Yu Xin, Sunlu Zeng, Lu Fan, Youzheng Wu, Xiaodong He
https://arxiv.org/abs/2509.12647

PAC: Pronunciation-Aware Contextualized Large Language Model-based Automatic Speech Recognition
This paper presents a Pronunciation-Aware Contextualized (PAC) framework to address two key challenges in Large Language Model (LLM)-based Automatic Speech Recognition (ASR) systems: effective pronunciation modeling and robust homophone discrimination. Both are essential for raw or long-tail word recognition. The proposed approach adopts a two-stage learning paradigm. First, we introduce a pronunciation-guided context learning method. It employs an interleaved grapheme-phoneme context modeling …

Hi-DARTS: Hierarchical Dynamically Adapting Reinforcement Trading System
Hoon Sagong, Heesu Kim, Hanbeen Hong
https://arxiv.org/abs/2509.12048 https://arxi…

Hi-DARTS: Hierarchical Dynamically Adapting Reinforcement Trading System
Conventional autonomous trading systems struggle to balance computational efficiency and market responsiveness due to their fixed operating frequency. We propose Hi-DARTS, a hierarchical multi-agent reinforcement learning framework that addresses this trade-off. Hi-DARTS utilizes a meta-agent to analyze market volatility and dynamically activate specialized Time Frame Agents for high-frequency or low-frequency trading as needed. During back-testing on AAPL stock from January 2024 to May 2025, H…

Atomic perspective on the topological magnetism in kagome metal Co3Sn2S2
Guowei Liu, Wei Song, Titus Neupert, M. Zahid Hasan, Hanbin Deng, Jia-Xin Yin
https://arxiv.org/abs/2508.11140

Atomic perspective on the topological magnetism in kagome metal Co3Sn2S2
Topological quantum materials with kagome lattices have attracted intense interest due to their unconventional electronic structures, which exhibit nontrivial topology, anomalous magnetism, and electronic correlations. Among these, Co3Sn2S2 stands out as a prototypical kagome metal, uniquely combining intrinsic ferromagnetism with topologically nontrivial electronic states. This perspective presents a systematic overview of recent advances in studying kagome metal Co3Sn2S2 achieved through scan…

Bill McKibben compares what China is doing for the planet - and why the US is getting this badly wrong
I am now about halfway through "Falter" his 2019 book - which is making me a bit depressed, but his current writing is cheering me up!

A Tale of Two Countries
Two superpowers, one behaving pathetically

What would war between EU and Russia actually look like: think WW1 style attrition and the absolute collapse of a way of life that many of us are very comfortable with.
@… is as ever to the point in this one.
https://youtu.be/HwnBnsQBeOA

Over the weekend the orange menace decided visitors to the USA must be interviewed in their home countries to apply for a visa. Wait-list can take up to a year. This is insane. He's so desperate for support from the meth-eating sister-humping xenophobic hillbillies that make up his eroding political base that he's turning the United States into Soviet Russia. I've been to nearly 30 countries. Some required visas in advance but none of them, not even Russia and China, required suc…

NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale
NextStep Team, Chunrui Han, Guopeng Li, Jingwei Wu, Quan Sun, Yan Cai, Yuang Peng, Zheng Ge, Deyu Zhou, Haomiao Tang, Hongyu Zhou, Kenkun Liu, Ailin Huang, Bin Wang, Changxin Miao, Deshan Sun, En Yu, Fukun Yin, Gang Yu, Hao Nie, Haoran Lv, Hanpeng Hu, Jia Wang, Jian Zhou, Jianjian Sun, Kaijun Tan, Kang An, Kangheng Lin, Liang Zhao, Mei Chen, Peng Xing, Rui Wang, Shiyu Liu, Shutao Xia, Tianhao You, Wei Ji…

NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale
Prevailing autoregressive (AR) models for text-to-image generation either rely on heavy, computationally-intensive diffusion models to process continuous image tokens, or employ vector quantization (VQ) to obtain discrete tokens with quantization loss. In this paper, we push the autoregressive paradigm forward with NextStep-1, a 14B autoregressive model paired with a 157M flow matching head, training on discrete text tokens and continuous image tokens with next-token prediction objectives. Next…