Tootfinder

'Want to Hang By a Tree?': Tesla Supervisor Said Only Black Workers Who’d Accept Being Called the N-Word Should Be Hired, Lawsuit Claims
https://atlantablackstar.com/2025/09/13/tesla-supervisor-said-only-black-workers-whod-accept-being-called-the-n-word-should-be-hired/

Elk: Exploring the Efficiency of Inter-core Connected AI Chips with Deep Learning Compiler Techniques
Yiqi Liu, Yuqi Xue, Noelle Crawford, Jilong Xue, Jian Huang
https://arxiv.org/abs/2507.11506

Elk: Exploring the Efficiency of Inter-core Connected AI Chips with Deep Learning Compiler Techniques
To meet the increasing demand of deep learning (DL) models, AI chips are employing both off-chip memory (e.g., HBM) and high-bandwidth low-latency interconnect for direct inter-core data exchange. However, it is not easy to explore the efficiency of these inter-core connected AI (ICCA) chips, due to a fundamental tussle among compute (per-core execution), communication (inter-core data exchange), and I/O (off-chip data access). In this paper, we develop Elk, a DL compiler framework to maximiz…

SmokeSVD: Smoke Reconstruction from A Single View via Progressive Novel View Synthesis and Refinement with Diffusion Models
Chen Li, Shanshan Dong, Sheng Qiu, Jianmin Han, Zan Gao, Kemeng Huang, Taku Komura
https://arxiv.org/abs/2507.12156

SmokeSVD: Smoke Reconstruction from A Single View via Progressive Novel View Synthesis and Refinement with Diffusion Models
Reconstructing dynamic fluids from sparse views is a long-standing and challenging problem, due to the severe lack of 3D information from insufficient view coverage. While several pioneering approaches have attempted to address this issue using differentiable rendering or novel view synthesis, they are often limited by time-consuming optimization and refinement processes under ill-posed conditions. To tackle above challenges, we propose SmokeSVD, an efficient and effective framework to progress…

Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation
Harold Haodong Chen, Haojian Huang, Qifeng Chen, Harry Yang, Ser-Nam Lim
https://arxiv.org/abs/2508.10858

Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation
Recent advancements in video generation have enabled the creation of high-quality, visually compelling videos. However, generating videos that adhere to the laws of physics remains a critical challenge for applications requiring realism and accuracy. In this work, we propose PhysHPO, a novel framework for Hierarchical Cross-Modal Direct Preference Optimization, to tackle this challenge by enabling fine-grained preference alignment for physically plausible video generation. PhysHPO optimizes vid…

Generic continuum model formalism for moir\'e superlattice systems
Bo Xie, Jianqi Huang, Jianpeng Liu
https://arxiv.org/abs/2509.11747 https://arxiv.or…

Generic continuum model formalism for moiré superlattice systems
The moiré superlattice system provides an excellent platform for exploring various novel quantum phenomena. To theoretically tackle the diverse correlated and topological states emerging from moiré superlattices, one usually adopts an effective low-energy continuum model based on which the electron-electron effects are further considered. However, the construction of an accurate continuum model remains a challenging task, particularly for complex moiré superlattices such as twisted transitio…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[3/3]:
- Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation
Li, Du, Yu, Li, Zhao, Liu, Jiang, Zhu, Huang

'Honk If You Hate Elon:' Two Days of Protest at the Tesla Diner https://www.404media.co/honk-if-you-hate-elon-two-days-of-protest-at-the-tesla-diner/

In May 2025, a high-profile lunch in Riyadh brought together Donald Trump,
the Crown Prince,
and a group of Silicon Valley billionaires and executives.
The guest list assembled by Elon Musk (Tesla, xAI, SpaceX) and arriving by their own jets:
Sam Altman (OpenAI), Jensen Huang (Nvidia), Alex Karp (Palantir), Dara Khosrowshahi (Uber), Ruth Porat (Alphabet/Google), Alexandr Wang (Scale AI), Travis Kalanick (Cloud Kitchens, former Uber CEO), Stephen Schwarzman (Blackstone…

Mad Kings and Saudi Princes
Award winning author and futurist Albert Bates writes about ecovillages, permaculture, negative emission technology, drawdown, and climate solutions.

RoboMatch: A Mobile-Manipulation Teleoperation Platform with Auto-Matching Network Architecture for Long-Horizon Manipulation
Hanyu Liu, Yunsheng Ma, Jiaxin Huang, Keqiang Ren, Jiayi Wen, Yilin Zheng, Baishu Wan, Pan Li, Jiejun Hou, Haoru Luan, Zhihua Wang, Zhigong Song
https://arxiv.org/abs/2509.08522…

RoboMatch: A Mobile-Manipulation Teleoperation Platform with Auto-Matching Network Architecture for Long-Horizon Manipulation
This paper presents RoboMatch, a novel unified teleoperation platform for mobile manipulation with an auto-matching network architecture, designed to tackle long-horizon tasks in dynamic environments. Our system enhances teleoperation performance, data collection efficiency, task accuracy, and operational stability. The core of RoboMatch is a cockpit-style control interface that enables synchronous operation of the mobile base and dual arms, significantly improving control precision and data co…

AD-AVSR: Asymmetric Dual-stream Enhancement for Robust Audio-Visual Speech Recognition
Junxiao Xue, Xiaozhen Liu, Xuecheng Wu, Xinyi Yin, Danlei Huang, Fei Yu
https://arxiv.org/abs/2508.07608

AD-AVSR: Asymmetric Dual-stream Enhancement for Robust Audio-Visual Speech Recognition
Audio-visual speech recognition (AVSR) combines audio-visual modalities to improve speech recognition, especially in noisy environments. However, most existing methods deploy the unidirectional enhancement or symmetric fusion manner, which limits their capability to capture heterogeneous and complementary correlations of audio-visual data-especially under asymmetric information conditions. To tackle these gaps, we introduce a new AVSR framework termed AD-AVSR based on bidirectional modality enh…