In my most recent post, I introduced a corrigibility transformation that could take an arbitrary goal over external environments and define a corrigible goal with no hit to performance. That post focused on corrigibility and deception in training, which are some of the biggest problems in AI alignment, but the underlying mechanism has broader applicability. In […]
Getting rid of them isn’t straightforward—or cheap. Users have been forced to resort to regenerating clips (which costs them more money), using external subtitle-removing tools, or cropping their videos to get rid of the subtitles altogether. Josh Woodward, vice president of Google Labs and Gemini, posted on X on June 9 that Google had developed
Darren Riley: Hi. Thanks for having me. Megan: Thank you ever so much for being with us. To get us started, let’s just talk a bit about JustAir. How did the idea for the company come about, and what does your company do as well? Darren: Yeah, absolutely. The real thesis of JustAir, is really
Epistemic status: This essay grew out of critique. After writing about relational alignment, someone said, “Cute, but it doesn’t solve deception.” At first I resisted that framing. Then I realised, deception isn’t a root problem, it’s a symptom. A sign that honesty is too costly. This piece reframes deception as adaptive, and explores how to
arXiv:2507.10409v1 Announce Type: cross Abstract: This study addresses the challenge of balancing energy efficiency with performance in AI/ML models, focusing on DeepRX, a deep learning receiver based on a fully convolutional ResNet architecture. We evaluate the energy consumption of DeepRX, considering factors including FLOPs/Watt and FLOPs/clock, and find consistency between estimated and actual energy usage,
[Submitted on 25 Jun 2025 (v1), last revised 14 Jul 2025 (this version, v2)] View a PDF of the paper titled A Complete Loss Landscape Analysis of Regularized Deep Matrix Factorization, by Po Chen and 2 other authors View PDF HTML (experimental) Abstract:Despite its wide range of applications across various domains, the optimization foundations of
[Submitted on 15 Nov 2024 (v1), last revised 13 Jul 2025 (this version, v2)] View a PDF of the paper titled CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation, by Dengke Zhang and 2 other authors View PDF HTML (experimental) Abstract:Open-vocabulary semantic segmentation aims to assign semantic labels to each pixel without being
[Submitted on 19 Feb 2025 (v1), last revised 14 Jul 2025 (this version, v2)] Authors:Maiya Goloburda, Nurkhan Laiyk, Diana Turmakhan, Yuxia Wang, Mukhammed Togmanov, Jonibek Mansurov, Askhat Sametov, Nurdaulet Mukhituly, Minghan Wang, Daniil Orel, Zain Muhammad Mujahid, Fajri Koto, Timothy Baldwin, Preslav Nakov View a PDF of the paper titled Qorgau: Evaluating LLM Safety in
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
arXiv:2507.09864v1 Announce Type: cross Abstract: Model Predictive Control (MPC)-based Reinforcement Learning (RL) offers a structured and interpretable alternative to Deep Neural Network (DNN)-based RL methods, with lower computational complexity and greater transparency. However, standard MPC-RL approaches often suffer from slow convergence, suboptimal policy learning due to limited parameterization, and safety issues during online adaptation. To
