Tootfinder

Post-Training Large Language Models via Reinforcement Learning from Self-Feedback
Carel van Niekerk, Renato Vukovic, Benjamin Matthias Ruppik, Hsien-chin Lin, Milica Ga\v{s}i\'c
https://arxiv.org/abs/2507.21931

Post-Training Large Language Models via Reinforcement Learning from Self-Feedback
Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks. We present Reinforcement Learning from Self-Feedback (RLSF), a post-training stage that uses the model's own confidence as an intrinsic reward, mimicking how humans learn in the absence of external feedback. After a frozen LLM generates several chain-of-thought solutions, we define and compute the confidence of each final answer span and rank the traces ac…

Demonstrating Interoperable Channel State Feedback Compression with Machine Learning
Dani Korpi, Rachel Wang, Jerry Wang, Abdelrahman Ibrahim, Carl Nuzman, Runxin Wang, Kursat Rasim Mestav, Dustin Zhang, Iraj Saniee, Shawn Winston, Gordana Pavlovic, Wei Ding, William J. Hillery, Chenxi Hao, Ram Thirunagari, Jung Chang, Jeehyun Kim, Bartek Kozicki, Dragan Samardzija, Taesang Yoo, Andreas Maeder, Tingfang Ji, Harish Viswanathan

Demonstrating Interoperable Channel State Feedback Compression with Machine Learning
Neural network-based compression and decompression of channel state feedback has been one of the most widely studied applications of machine learning (ML) in wireless networks. Various simulation-based studies have shown that ML-based feedback compression can result in reduced overhead and more accurate channel information. However, to the best of our knowledge, there are no real-life proofs of concepts demonstrating the benefits of ML-based channel feedback compression in a practical setting, …

This https://arxiv.org/abs/2411.06332 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Quantum feedback induced entanglement relaxation and dynamical phase transition in monitored free fermion chains with Wannier-Stark ladder
In recent years, measurement induced entanglement transitions (MIETs) have attracted significant attention. However, the dynamical transition associated with the feedback induced skin effect, which exhibits a wealth of intriguing phenomena, has not been fully understood. In this work, we investigate a dynamical phase transition in a tilted free-fermion chain under measurement-feedback protocols, emphasizing the particle density and entanglement entropy dynamics. We reveal a feedback induced ski…

A Practical Guide for Supporting Formative Assessment and Feedback Using Generative AI
Sapolnach Prompiengchai, Charith Narreddy, Steve Joordens
https://arxiv.org/abs/2505.23405

A Practical Guide for Supporting Formative Assessment and Feedback Using Generative AI
Formative assessment is a cornerstone of effective teaching and learning, providing students with feedback to guide their learning. While there has been an exponential growth in the application of generative AI in scaling various aspects of formative assessment, ranging from automatic question generation to intelligent tutoring systems and personalized feedback, few have directly addressed the core pedagogical principles of formative assessment. Here, we critically examined how generative AI, e…

But look at the 4 on that! Don't these sundial makers know how to write Roman numerals? Where is the QC!?
https://social.lol/@adam/114880680239385409

Republican Sen. Thom Tillis of North Carolina won't run in 2026 after opposing Trump's bill (Associated Press)
https://apnews.com/article/tillis-senate-north-carolina-trump-reelection-republicans-382f72ff5228d864b38009904cbc4e6b
http://www.memeorandum.com/250629/p84#a250629p84

Decoding AGN Feedback with X-arithmetic: From Morphology to Physical Mechanisms
Hannah McCall, Irina Zhuravleva, Eugene Churazov, Congyao Zhang, William Forman, Christine Jones, Yuan Li
https://arxiv.org/abs/2506.21859

Decoding AGN Feedback with X-arithmetic: From Morphology to Physical Mechanisms
Feedback from Active Galactic Nuclei (AGN) is a key process in the evolution of massive halos in the Universe. New observational information on feedback is crucial for improving the implementation of the physics in numerical models. In this work, we apply a novel image-manipulation technique, termed 'X-arithmetic', to a sample of 15 galaxy clusters and groups deeply observed with Chandra. This technique decomposes perturbations in feedback-dominated regions into images excluding either (1) weak…

Original post: https://bsky.app/profile/did:plc:35rfycqhqobkeeiv4bv4qip7/post/3lsr5ihgjve2z

🚚 Move your #Azure resources across subscriptions or resource groups—without downtime!
Use CLI, PowerShell, Python, or REST API to stay flexible and in control. ⚙️📦 Just update those resource IDs! #CloudManagement
Learn more: