Tootfinder

Very excited about this! Code to access GRIN will help lots of Google Books partners, and the example might open other doors, as well as the obvious benefits of access to data!
'Institutional Books 1.0: A 242B token dataset from Harvard Library's collections, refined for accuracy and usability' https://arxiv.org/abs/2506…

Institutional Books 1.0: A 242B token dataset from Harvard Library's collections, refined for accuracy and usability
Large language models (LLMs) use data to learn about the world in order to produce meaningful correlations and predictions. As such, the nature, scale, quality, and diversity of the datasets used to train these models, or to support their work at inference time, have a direct impact on their quality. The rapid development and adoption of LLMs of varying quality has brought into focus the scarcity of publicly available, high-quality training data and revealed an urgent need to ground the steward…

UCLA Chancellor Julio Frenk and UC President James B. Milliken have appeared to reject Trump administration demands tied to the restoration of federal funding. The demands reportedly include a large monetary settlement, an end to diversity, equity, and inclusion practices, and a rollback of transgender rights on campus. That rollback would ban transgender students from participating in sports, living in dorms, and likely using bathrooms …

UCLA Rejects Trump Demands To Capitulate To Anti-Trans Policies—For Now
The university has refused to bow to the President’s sweeping list of anti-transgender demands—bucking a growing trend of large universities that have caved to similar pressure.

Urban Life 101 🏙️
城市生活 101 🏙️
📷 Nikon FE
🎞️Ilford FP4 Plus, expired 1995
buy me ☕️ ?/请我喝杯☕️？
#filmphotography

Yiding Cao Geld mit PayPal.Me senden
Folgen Sie dem Link PayPal.Me/dingsterdingster und geben Sie den Betrag ein. Es ist bequem und sicher. Sie haben noch kein PayPal-Konto? Kein Problem.

The Emergence of Abstract Thought in Large Language Models Beyond Any Language
Yuxin Chen, Yiran Zhao, Yang Zhang, An Zhang, Kenji Kawaguchi, Shafiq Joty, Junnan Li, Tat-Seng Chua, Michael Qizhe Shieh, Wenxuan Zhang
https://arxiv.org/abs/2506.09890

The Emergence of Abstract Thought in Large Language Models Beyond Any Language
As large language models (LLMs) continue to advance, their capacity to function effectively across a diverse range of languages has shown marked improvement. Preliminary studies observe that the hidden activations of LLMs often resemble English, even when responding to non-English prompts. This has led to the widespread assumption that LLMs may "think" in English. However, more recent results showing strong multilingual performance, even surpassing English performance on specific tasks in other…

Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation
Youguang Xing, Xu Luo, Junlin Xie, Lianli Gao, Hengtao Shen, Jingkuan Song
https://arxiv.org/abs/2508.06426

Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation
Generalist robot policies trained on large-scale datasets such as Open X-Embodiment (OXE) demonstrate strong performance across a wide range of tasks. However, they often struggle to generalize beyond the distribution of their training data. In this paper, we investigate the underlying cause of this limited generalization capability. We identify shortcut learning -- the reliance on task-irrelevant features -- as a key impediment to generalization. Through comprehensive theoretical and empirical…

I finally got rid of the old bed I’d kept since moving in, so the room feels pretty empty right now.
I’m in the process of reorganizing everything and plan to turn this space into my own anarchist sanctuary.
Soon, I’ll add a bookshelf and more anarchist art to the wall, right next to the communist hammer and sickle symbol.
#Declutter

Scaling RL to Long Videos
Yukang Chen, Wei Huang, Baifeng Shi, Qinghao Hu, Hanrong Ye, Ligeng Zhu, Zhijian Liu, Pavlo Molchanov, Jan Kautz, Xiaojuan Qi, Sifei Liu, Hongxu Yin, Yao Lu, Song Han
https://arxiv.org/abs/2507.07966

Scaling RL to Long Videos
We introduce a full-stack framework that scales up reasoning in vision-language models (VLMs) to long videos, leveraging reinforcement learning. We address the unique challenges of long video reasoning by integrating three critical components: (1) a large-scale dataset, LongVideo-Reason, comprising 52K long video QA pairs with high-quality reasoning annotations across diverse domains such as sports, games, and vlogs; (2) a two-stage training pipeline that extends VLMs with chain-of-thought supe…

Fair Diversity Maximization with Few Representatives
Florian Adriaens, Nikolaj Tatti
https://arxiv.org/abs/2506.08110 https://arxiv.o…

Fair Diversity Maximization with Few Representatives
Diversity maximization problem is a well-studied problem where the goal is to find $k$ diverse items. Fair diversity maximization aims to select a diverse subset of $k$ items from a large dataset, while requiring that each group of items be well represented in the output. More formally, given a set of items with labels, our goal is to find $k$ items that maximize the minimum pairwise distance in the set, while maintaining that each label is represented within some budget. In many cases, one is …

Understanding the Performance and Power of LLM Inferencing on Edge Accelerators
Mayank Arya, Yogesh Simmhan
https://arxiv.org/abs/2506.09554 https://

Understanding the Performance and Power of LLM Inferencing on Edge Accelerators
Large Language Models (LLMs) have demonstrated exceptional benefits to a wide range of domains, for tasks as diverse as code generation and robot navigation. While LLMs are usually served from cloud data centers, mission-critical and privacy-sensitive applications may require local hosting of open LLM models. Given the large GPU memory footprint needed for LLMs, edge accelerators such as Nvidia Jetson Orin AGX with 64GB of shared GPU-CPU RAM are a compelling choice. However, the feasibility and…

CD-TVD: Contrastive Diffusion for 3D Super-Resolution with Scarce High-Resolution Time-Varying Data
Chongke Bi, Xin Gao, Jiangkang Deng, Guan
https://arxiv.org/abs/2508.08173 h…

CD-TVD: Contrastive Diffusion for 3D Super-Resolution with Scarce High-Resolution Time-Varying Data
Large-scale scientific simulations require significant resources to generate high-resolution time-varying data (TVD). While super-resolution is an efficient post-processing strategy to reduce costs, existing methods rely on a large amount of HR training data, limiting their applicability to diverse simulation scenarios. To address this constraint, we proposed CD-TVD, a novel framework that combines contrastive learning and an improved diffusion-based super-resolution model to achieve accurate 3…