What the smart people are recommending. 7861 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.
“Then, we train a GAN on these data and apply a GPT-3.5 based data augmentation technique to synthesize an extended sarcastic comment dataset, named SinaSarc.”
“The code is available at https://github.com/Pepper66/DMLE.”
“The code is available at github.com/ryehr/RRC_steganography.”
“Code and examples: https://github.com/thcxiker/R2A-Attack.”
“Our code is available at https://github.com/deep-real/GenCircuit.”
“The model is implemented in PyTorch (https://github.com/anders-s-olsen/shiftstretchNMF).”
“The code and data is available at https://github.com/asuvarna31/supernova.”
“The full simulation codebase and FPGA estimation scripts are publicly available at https://github.com/therealdeadbeef/aerospace-fl-quantization.”
“The CrashSight benchmark, including the full dataset and code, is accessible at https://mcgrche.github.io/crashsight.”
“To support this, we present InstVL, a large-scale dataset (2 million images, 50,000 videos) with dual-granularity annotations: holistic scene captions and dense, grounded instance descriptions.”
“The code and benchmark will be available on GitHub.”
“We publicly release our datasets, reward models, and benchmarks to facilitate reproducible research in safety-aware medical alignment.”
“We publicly release our datasets, reward models, and benchmarks to facilitate reproducible research in safety-aware medical alignment.”
“The MATLAB code used in the numerical experiments is also made freely available to support the reproducibility of the results.”
“See project page: https://github.com/ARC0127/Fisher-Decorator.”
“We benchmark eight state-of-the-art VAD methods on AnoVox, the largest synthetic dataset for anomaly detection in autonomous driving.”
“Our dataset and code will be released at https://github.com/Young-Zhen/VRU_Interpret .”
“We release data and code at https://njucckevin.github.io/openmobile/ to bridge the data gap and facilitate broader mobile agent research.”
“Our code repository is available online at https://github.com/ponhvoan/internal-variance.”
“Our code is available at https://github.com/figec/TTL.”
“We release the benchmark code as supplementary material to encourage the development of more robust scientific literature novelty metrics.”
“Our work is publicly available at https://hhi.fraunhofer.de/aml-demonstrator/made-benchmark.”
“You can just go to Adam Jacobs, just Google Adam Jacobs collection.”
“Code available at https://github.com/Weijiang-Xiong/OpenSkyTraffic”
“This paper rewrites our earlier draft around the system that was actually implemented and archived in the repository: a sample-level 1B to 7B cascade for the shared-8 EduBench benchmark.”
“Our source code is available at https://github.com/hkr04/RACER.”
“The implementation is available at https://github.com/Git-King-Zhan/LoReC.”
“The code is available at https://github.com/bjzgcai/CoPA.”
“The dataset construction pipeline and benchmark evaluation code are publicly available at https://github.com/pritesh-2711/pii-bench.”
“we propose a reactor-model-of-computation (MoC)-based approach, realized by the open-source Lingua Franca (LF) framework.”
“Code is available at: https://github.com/IMPACTSquad/Blast-Mamba”
“Code is available at https://github.com/KDEGroup/SWE-AGILE.”
“We present SemaClaw, an open-source multi-agent application framework that addresses these shifts by taking a step towards general-purpose personal AI agents through harness engineering.”
“Relax is available at https://github.com/rednote-ai/Relax.”
“Our code is available at https://github.com/Humphrey-0125/METRO.”
“Our code is available at https://github.com/ynklab/vlm-latent-piaa.”
“Our code and dataset are available at https://github.com/SCUNLP/METER .”
“To support related research, we also release PRM800K, the complete dataset of 800,000 step-level human feedback labels used to train our best reward model.”
“Our code is available at https://github.com/SungHo3268/SCRIPT.”
“The package is freely available at https://github.com/kyradelray/mcanalysis, with a no-code web interface at https://kyradelray.shinyapps.io/mcanalysis/.”
“Code, data and models are available at https://bijiaxihh.github.io/STOP”
“LiteParse hit 4.3K+ GitHub stars in a few weeks. Today it officially joins the LlamaIndex ecosystem, with its own page at https://www.llamaindex.ai/liteparse”
“AtomTwin.jl is an open-source Julia package for developing and simulating quantum protocols, hardware configurations and building digital twins for neutral-atom quantum processors and related atomic q…”
“To facilitate reuse, we release the datasets and the pre-trained models at https://github.com/tum-pbs/AeroTransformer.”
“We release our model(s) and training framework at: https://github.com/j0shmillar/physiolite.”
“The code to reproduce our results is open-sourced at https://github.com/kowndinya-renduchintala/heterogeneity-in-formal-linguistic-competence.”
“class NPTF(object):”
“To spur progress on domain shift, we also release GAP-VIR, a cross-platform (ground/aerial) VIS-IR patch dataset with 500K pairs, enabling rigorous evaluation of cross-domain generalization and adapta…”
“So there are two ways um to follow me online and the first the best way is uh through my YouTube channel predictive history and then I have a Substack uh which actually goes deep and analyzes um geopo…”
“For papers, prefer the arXiv link.”
“My project at OpenAI, for example, was within the scope of the Universe project, on an agent that was using keyboard and mouse to operate web pages.”
“Maybe an example from one of my repos that I think illustrates it well is called micrograd. I don't know if you're familiar with this.”
“The code is available at https://github.com/H-EmbodVis/NUMINA.”
“We hope that the simplicity and theory-friendly ecosystem offered by LeJEPA will reestablish self-supervised pre-training as a core pillar of AI research (GitHub repo)”
“It is a rewrite of [minGPT](https://github.com/karpathy/minGPT) that prioritizes teeth over education.”
“So go ahead and get clone.”
“And you can also use LMS to author the XML files and then you combine them into this exponential number of procedurally generated rooms and putting all of them together. This is a project, an open sou…”
“in terms of the training data for the tokenizer we use fine web 2 which you can access \n publicly in hugging face”
“Make sure your codebase is correctly structured. Your file structure should look like this (here we use the `keras_tuner` package as an example)”
“This brings us directly to a project called Superpowers. Right? It was created by a very clever developer who goes by Obra. Superpowers adds real software engineering discipline directly to claude cod…”
“This brings us to a project called Hermes Agent. It was built by the brilliant team over at Noose Research. Hermes is a completely self-improving AI agent framework.”
“llm.rs by @Yijun Yu: a Rust rewrite with the aim to have same performance”
“LOBSTER_BOOTSTRAP.md activated”
“A simple example demonstrating the power of Next.js and RSC to "server-render data", rather than server-render HTML.”
“If you're manually doing any repetitive task right now, there's probably an n8n template for it.”
“If your agent needs to read the internet, this is the standard.”
“If you're the type who thinks better visually, and the idea of writing orchestration code makes you want to close your laptop, this is your tool.”
“If you've ever sat there watching a single agent think for 10 minutes while you have four other things that need doing, this solves the problem immediately.”
“If you want to explore beyond what I covered today, start here. It's regularly updated, and the community contributes to it.”
“If you want to learn how to make your own, read through their examples first.”
“The code is available at https://github.com/raktimgg/osvi-wm.”
“Code, data and checkpoints are available at https://github.com/facebookresearch/jepa-wms.”
“Then add gbrain straight from the GitHub repo.”
“The repo link is on screen and it is worth reading the readme, the skill pack, the schema and the verify runbook together.”
“Run git clone https://github.com/cbor/test-vectors”
“the auto research project from Karpathy that came out this weekend... we now have a group of tinkerers who are setting up their open clause and now setting up large language models and now trying to t…”
“Models: https://huggingface.co/collections/SandyResearch/parcae”
“llm.🔥 by @dorjeduck: a Mojo port of this project”
“For additional terms and responsible gaming resources, see dkg.co/audio. Limited time offer.”
“Visit agency.org and add your support. That's agncy.org.”
“The best introduction to the llm.c repo today is reproducing the GPT-2 (124M) model. Discussion #481 steps through this in detail.”
“It's completely free. Everybody should try it. And you just go to ampfarm.cool. ... It's open source on GitHub. Check it out.”
“On top of this you need the cuDNN frontend, but this is just header files. Simply clone the repo to your disk.”
“AMD support: llm.c by @anthonix: support for AMD devices, such as the 7900 XTX”
“llm.cs by @azret: a C# port of this project”
“Llm.cs by @nietras: a C# port of this project with focus on easy to get started on any platform. Clone and run ✅”
“llm.cpp by @gevtushenko: a port of this project using the CUDA C++ Core Libraries”
“gpu.cpp by @austinvhuang: a library for portable GPU compute in C++ using native WebGPU.”
“llm.go by @joshcarp: a Go port of this project”
“llm.java by @harryjackson: a Java port of this project”
“llm.metal by @regrettable-username: LLM training in simple, raw C/Metal Shading Language”
“llm.zig by @saimirbaci: a Zig port of this project”
“llm.tpc by @abhilash1910: a Habana Gaudi2 port of this project”
“llm.nim by @Vindaar: a Nim port of this project”
“if you go to the generative AI lab at Wharton, we have a whole bunch of creative common prompts that we've released that are designed for teaching and you can modify for yourself.”
“there was a training run that happened in this crypto project called Bit Tensor Subnet 3. They managed to train a 4 billion parameter llama model totally distributed with a bunch of people contributin…”
“I actually built one, uh that I have myself... there is a QR code that you can scan and get the GitHub repo. It's all open source.”
“they built the LDK, which is a lightning development kit, the Bitcoin development kit. They're up to 10 people right now.”
“Code: https://github.com/rbalestr-lab/llm-jepa.”
“`mistral-finetune` is a light-weight codebase that enables memory-efficient and performant finetuning of Mistral's models.”