What the smart people are recommending. 7794 books, tools, and products endorsed by the thinkers absorb.md tracks. Ranked by how many times each has been recommended across compiled podcasts, papers, posts, and tweets.
βCompanion paper arXiv:2603.20997 (Basu, 2026) defines the routing diagnostic task.β
βWe present failure cases of symbolic evaluation in two popular frameworks, Lighteval and SimpleRL, and compare them to our approach, demonstrating clear improvements over commonly used methods.β
βWe present failure cases of symbolic evaluation in two popular frameworks, Lighteval and SimpleRL, and compare them to our approach, demonstrating clear improvements over commonly used methods.β
βTHIS REPOSITORY IS DEPRECATED. USE THE MODULE `keras.applications` INSTEAD.β
βThis repository contains code for the following Keras models: - VGG16β
βThis repository contains code for the following Keras models: - VGG19β
βThis repository contains code for the following Keras models: - ResNet50β
βOur core technical contribution is the \textbf{DDPO} algorithm,Diversity Driven Policy Optimization, a multi-turn GRPO-based approach designed to preserve dialogue diversity while holistically optimizβ¦β
βThis repository contains code for the following Keras models: - CRNN for music taggingβ
βVery Deep Convolutional Networks for Large-Scale Image Recognition - please cite this paper if you use the VGG models in your work.β
βDeep Residual Learning for Image Recognition - please cite this paper if you use the ResNet model in your work.β
βRethinking the Inception Architecture for Computer Vision - please cite this paper if you use the Inception v3 model in your work.β
β# A hierarchical loss and its problems when classifying non-hierarchicallyβ
βWe propose CRAFT (Clustered Regression for Adaptive Filtering of Training data), a vectorization-agnostic selection method for training sequence-to-sequence models.β
βMusic-auto_tagging-kerasβ
βNew monster post: my own current perspective on the recent debates around techno-optimism, AI risks, and ways to avoid extreme centralization in the 21st century. https://vitalik.eth.limo/general/202β¦β
βin order to access full episodes of The Making Sense podcast you'll need to subscribe at samharris.orgβ
βBlog post by Yann LeCunβ
βTo resolve these challenges, we propose MADE-IT (Manifold-Aware Dynamic Expert Evolution and Implicit rouTing), an adaptive CMM method...β
βIn this paper, we present pliable rejection sampling (PRS), a new approach to rejection sampling, where we learn the sampling proposal using a kernel estimator.β
βThe code is available at https://github.com/Kanyooo/SOC-ICNN.β
βWe build upon this promising foundation and extend the method to work as an uncertainty estimation technique for already-trained artificial neural networks in the domain of regression. Our experimentsβ¦β
β(Calandriello et al. 2016) propose INK-Estimate, an algorithm that processes the dataset incrementally and updates RLS, effective dimension, and Nystrom approximations on-the-fly.β
βIn this paper we introduce SQUEAK, a new algorithm that builds on INK-Estimate but uses unnormalized RLS.β
βThe source code for the proposed RFLkPC method is publicly available at https://github.com/xuelin-xie/RFLkPC.β
βour podcast in january of 2018 it's an amazing story you should go back and check it outβ
βThere's a great book actually I was looking for it so I could show everybody yeah a very old book by a guy named Al Reese called the 22 Immutable Laws of Marketing and you know once in a while I'll juβ¦β
βA comprehensive simulation study shows that the conformalized SL achieves valid finite-sample coverage with competitive performance relative to the true data-generating mechanism. A central contributiβ¦β
βspeaking of which we have a brand new episode of the podcast out today about Joe Malone uh Joe Malone London the perfume brand it is an insane story it's like a magical reel andβ
βWe introduce HiLight, an Evidence Emphasis framework that decouples evidence selection from reasoning for frozen LLM solvers. HiLight avoids compressing or rewriting the input, which can discard or diβ¦β
βJAMstack ECommerce Professional provides a way to quickly get up and running with a fully configurable JAMstack E Commerce site.β
βTo learn more how this works, check out the Tailwind documentation [here](https://tailwindcss.com/docs).β
βBased on this observation, we propose QuantClaw, a plug-and-play precision routing plugin that dynamically assigns precision according to task characteristics.β
βWe validated our method, QDTraj, by generating diverse trajectories in simulation and deploying them in the real world. QDTraj generates at least 5 times more diverse trajectories for both hinge and sβ¦β
βThe increasing adoption of AI systems in hiring has raised concerns about algorithmic bias and accountability, prompting regulatory responses including the EU AI Act, NYC Local Law 144, and Colorado'sβ¦β
βThe increasing adoption of AI systems in hiring has raised concerns about algorithmic bias and accountability, prompting regulatory responses including the EU AI Act, NYC Local Law 144, and Colorado'sβ¦β
βWe assessed the generalization of our method over 30 articulations of the PartNetMobility articulated object dataset, with an average of 704 different trajectories by task. Code is publicly available β¦β
βThe increasing adoption of AI systems in hiring has raised concerns about algorithmic bias and accountability, prompting regulatory responses including the EU AI Act, NYC Local Law 144, and Colorado'sβ¦β
βyou can use flux or mlj.jl both of those are i think viableβ
βMuDABench is available at https://github.com/Zhanli-Li/MuDABench.β
βAudio samples are available at https://qiangchunyu.github.io/UniSonate/.β
βIn this paper, we formulate routing as a budget allocation problem and identify marginal gain... we propose RouteLMT (routing for LLM-based MT), an efficient in-model router... Extensive experiments dβ¦β
βfor ease of finding you can find the previous conversation with nick zabo on bitcoin and smart contracts and other core concepts at tim dot blog forward slash bitcoinβ
βIn this whitepaper, we introduce the Snake Optimizer for efficiently and quickly solving such optimization problems by leveraging concepts in artificial intelligence, dynamic programming, and graph opβ¦β
β# Focus beyond quadratic speedups for error-corrected quantum advantageβ
βyou can also find this current conversation with vitalik on all things ethereum at tim dot blog forward slash ethereum that's e-t-h-e-r-e-u-mβ
β# 2025 Conventions _Blog post by Laura Martin_ https://lauramartinart.com/2025/02/09/2025-conventions/β
βThis episode is brought to you by peak pique in their brand new supplement daily immune vitamin c optimized for absorptionβ
βProject page: https://muzhancun.github.io/preprints/DROL.β
βTTS-PRISM is open-source, with code and checkpoints at https://github.com/xiaomi-research/tts-prism.β
βyou had a really good post on your blog saying endnotes on 2020 and it was about a lot more than just cryptoβ
βHere, by measuring the time-dependent evolution and fluctuation of out-of-time-order correlators, we experimentally investigate the dynamics of quantum scrambling on a 53-qubit quantum processor. We eβ¦β
βCode is available at https://github.com/shuowl/llm-source-balancing.β
βCode is available at https://github.com/BU-DEPEND-Lab/SpecRLBench.β
βThis course is using the :sparkles: open source project [reveal.js](https://github.com/hakimel/reveal.js/). In some cases weβve made changes to the history so it would behave during class, so head to β¦β
βOverall, H-optimus-1 achieves the strongest survival prediction performance.β
β# Implicit Rank-Minimizing Autoencoderβ
βThe Stupid are dangerous to society β and to themselves β’ Attempting to control the Stupid for political gain always backfires π https://t.co/iYxW0pzef7 #ProfGShowβ
β_ArXiv paper co-authored by Hartmut Neven_β
βNotably, the compact distilled model H0-mini slightly outperforms its larger teacher model H-optimus-0, despite using fewer than 8% of the parameters and enabling significantly faster feature extractiβ¦β
βThe platform is publicly available at Energy-Arena.org.β
βWe propose Hyperparameter-Divergent Ensemble Training (HDET), a method that repurposes these replicas for simultaneous learning rate exploration at negligible communication overhead.β
βHDET is implemented as a drop-in replacement for PyTorch's OneCycleLR scheduler, requiring no changes to model architecture, optimizer, or data pipeline.β
βWe demonstrate the application of the Google Sycamore superconducting qubit quantum processor to combinatorial optimization problems with the quantum approximate optimization algorithm (QAOA).β
βOur code, benchmark, and model are released at https://shiyi-zh0408.github.io/projectpages/Meta-CoT/β
βThe system uses instruction-tuned qwen3-embedding-0.6B embeddings...Qwen3 embeddings with 300-token chunk size achieved 94.6% accuracy on a clinical question-answering benchmark.β
βOur code and data are available at https://github.com/MAPS-research/SHaPEβ
βDV-World provides a realistic testbed to steer development toward the versatile expertise required in enterprise workflows. Our data and code are available at this project page.β
βIts closure leaves behind non-updatable benchmarks, irreproducible results, and ultimately a field at risk of perpetuating these issues by turning to closed-source LLMs.β
βSo you've written the book, Recession, the real reasons economies shrink and what to do about it.β
βIf you're a business owner or investor who's tired of overpaying taxes, the Wealth Ability Accelerator is your next step. You'll have the opportunity to work directly with me for 80% less than my stanβ¦β
βOxyGent is publicly available at https://oxygent.jd.com/β
βthen some professors at 11 told me look there is this organization the belgian american educational foundation baef and they give out fellowships for a first year of study in the us and so i applied fβ¦β
βand andrew indeed uh if you look at online courses for machine learning it's a it's also a course i frequently recommend to uh to my studentsβ
βOur code and data are available at https://github.com/bigspinai/bigspin-fluency-outcomesβ
βWe propose a quantum algorithm for inferring the molecular nuclear spin Hamiltonian from time-resolved measurements of spin-spin correlators, which can be obtained via nuclear magnetic resonance (NMR)β¦β
βyou know for me i've read the alan turing 1950 paper computing machinery and intelligence paper back before i knew how to code and i remember reading it you know it lays out the turing test but then iβ¦β
βThe resulting corpus comprises Β± 35 billion tokens across the medical domain in about 100 million documents, freely available on Hugging Face.β
βthe most widely adopted multilingual base (Chatterbox, 23 languages) does not even tokenise Telugu or Tamilβ
βwe have a gpt-3 fine-tuning api these days um you know we'll be rolling that out for codexβ
βon the fiction side I'm reading Roman gar who is a great French writer at the moment and everybody reads his bookβ
βthe best open-source bases (Chatterbox, Indic Parler-TTS, IndicF5) trail them on measured phonological dimensionsβ
βFor intra-sentential code-mix we add a third branch (IndicF5 + native-script transliteration) that drops code-mix LLM-WER from 0.80-0.85 to 0.14-0.27β
βWe release R6 LoRA weights (Apache-2.0), inference code and router (MIT), and a Gradio demo.β
βWe release R6 LoRA weights (Apache-2.0), inference code and router (MIT), and a Gradio demo.β
βBig techβs impending march into higher ed will bring more learning to more humans, and erode our humanity. #nomercynomalice https://www.profgalloway.com/post-corona-higher-ed/β
βWe introduce SOB (The Structured Output Benchmark), a multi-source benchmark spanning three source modalities: native text, images, and audio conversations.β
βData and code are available at https://github.com/qzhangFDU/faithfulness-qa-dataset.β
βget a copy of my latest book meaningful measurement of the customer experience now available on Amazon and other retailersβ
βI've long objected to the 'surveillance advertising' trope, for it trivializes actual surveillance under force of government, such as this, brought to us by the folks at Palantir. Gift link.β
βWe test whether the causal inner product of \citet{park2024linear} -- defined by the unembedding covariance $Ξ£$ -- enables cross-lingual concept transport.β
βand the arc challenge is one attempt to embody as many of these principles as possibleβ
βHere, we simulate the dynamics of the one-dimensional Fermi-Hubbard model using 16 qubits on a digital superconducting quantum processor. We observe separations in the spreading velocities of charge aβ¦β
βSo there's one approach that I was very excited about and that I thought was it's very cool and I really like it's it's called dreamcoder by Dr. Kevin Ellis and and folks Um, so check it out if you ifβ¦β
βwell I read papers that's what people should be writing uh generally science papers uh that's where the knowledge is and I will that's where the knowledge will likely remainβ
β# Do Robots powered by a Quantum Processor have the Freedom to swerve? _ArXiv paper co-authored by Hartmut Neven_β
βIf you want to become not a lone wolf, but a part of the Purple Patch coaching team, mentored directly by me as a part of a team that not just coaches individual athletes, but has an imprint on the huβ¦β
βAnd then on top of that, if you enjoy this episode and you want to chat, you want to dive into any of these topics, deeper info, purple patch fitness.com. You can schedule a call with me. It'll be a lβ¦β
βother people know me for the food books. I'm the worst dilemma in defense of food.β
βother people know me for the food books. I'm the worst dilemma in defense of food.β