Tootfinder

Promptimizer: User-Led Prompt Optimization for Personal Content Classification
Leijie Wang, Kathryn Yurechko, Amy X. Zhang
https://arxiv.org/abs/2510.09009 https://

Promptimizer: User-Led Prompt Optimization for Personal Content Classification
While LLMs now enable users to create content classifiers easily through natural language, automatic prompt optimization techniques are often necessary to create performant classifiers. However, such techniques can fail to consider how social media users want to evolve their filters over the course of usage, including desiring to steer them in different ways during initialization and iteration. We introduce a user-centered prompt optimization technique, Promptimizer, that maintains high perform…

Ava DuVernay, Olivia Colman & Yorgos Lanthimos Among Signatories Of Pledge To Boycott Israeli Film Institutions “Implicated In Genocide”
https://deadline.com/2025/09/film-workers-for-palestine-ava-duvernay-olivia-colman-1236511823/

K2-Think: A Parameter-Efficient Reasoning System
Zhoujun Cheng, Richard Fan, Shibo Hao, Taylor W. Killian, Haonan Li, Suqi Sun, Hector Ren, Alexander Moreno, Daqian Zhang, Tianjun Zhong, Yuxin Xiong, Yuanzhe Hu, Yutao Xie, Xudong Han, Yuqi Wang, Varad Pimpalkhute, Yonghao Zhuang, Aaryamonvikram Singh, Xuezhi Liang, Anze Xie, Jianshu She, Desai Fan, Chengqian Gao, Liqun Ma, Mikhail Yurochkin, John Maggs, Xuezhe Ma, Guowei He, Zhiting Hu, Zhengzhong Liu, Eric P. Xing

K2-Think: A Parameter-Efficient Reasoning System
K2-Think is a reasoning system that achieves state-of-the-art performance with a 32B parameter model, matching or surpassing much larger models like GPT-OSS 120B and DeepSeek v3.1. Built on the Qwen2.5 base model, our system shows that smaller models can compete at the highest levels by combining advanced post-training and test-time computation techniques. The approach is based on six key technical pillars: Long Chain-of-thought Supervised Finetuning, Reinforcement Learning with Verifiable Rewa…

There's no need to promote a lot from YT. But for Ken Thompson I gotta make an exception:
https://youtu.be/OmVHkL0IWk4?si=ZlC9k6yrSK15hk_I
And, yes, it's more than 4 hours but that's what a decent interview takes up. Slice it and watch chunks at your leisure! I…

"People are dying, and this the top policy agenda from my government? […] America is soulless, guys. […] I'm just so deeply sorry. This is… incredibly shameful."
https://youtu.be/yr5qJAztock?si=L33wF-B3aAjcUDNL&t=973
Thank you, Jake Broe

🇺🇦 #NowPlaying on BBCRadio3's #MusicPlanet
Astillero:
🎵 Catinga
#Astillero
https://open.spotify.com/track/2y4rJ0wQJesINCkIhDgPNt

Amplifying Two-Mode Squeezing in Nanomechanical Resonators
Muhdin Abdo Wodedo, Tesfay Gebremariam Tesfahannes, Tewodros Yirgashewa Darge, Mauro Pereira, Berihu Teklu
https://arxiv.org/abs/2508.18972

Amplifying Two-Mode Squeezing in Nanomechanical Resonators
Quantum squeezing plays a crucial role in enhancing the precision of quantum metrology and improving the efficiency of quantum information processing protocols. We thus propose a scheme to amplify two-mode squeezing in nanomechanical resonators, harnessing parametric amplification and two-tone laser controls. The red-detuned laser drives facilitate the cooling of the nanomechanical resonators down to their ground state and allow optimal quantum state transfer in the weak-coupling, resolved side…

Limitations of refinement methods for weak to strong generalization
Seamus Somerstep, Ya'acov Ritov, Mikhail Yurochkin, Subha Maity, Yuekai Sun
https://arxiv.org/abs/2508.17018

Limitations of refinement methods for weak to strong generalization
Standard techniques for aligning large language models (LLMs) utilize human-produced data, which could limit the capability of any aligned LLM to human level. Label refinement and weak training have emerged as promising strategies to address this superalignment problem. In this work, we adopt probabilistic assumptions commonly used to study label refinement and analyze whether refinement can be outperformed by alternative approaches, including computationally intractable oracle methods. We show…

🇺🇦 #NowPlaying on #BBC6Music's #NickGrimshaw
Yello:
🎵 Bostich
#Yello
https://neapolitansoulrecords.bandcamp.com/track/yello-bostich-ns-cut
https://open.spotify.com/track/365fQNeYERzuJLzfUEEhLl

Crosslisted article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[2/2]:
- Bridging Human and LLM Judgments: Understanding and Narrowing the Gap
Felipe Maia Polo, Xinhe Wang, Mikhail Yurochkin, Gongjun Xu, Moulinath Banerjee, Yuekai Sun