Matthew McKee Independent Researcher Adelaide, Australia sindecker@gmail.com · arxiv.org
Retrieving relevant past interactions from long-term conversational memory typically relies on large dense retrieval models (110M–1.5B parameters) or LLM-augmented indexing. We introduce SelRoute, a framework that routes each query to a specialized retrieval pipeline — lexical, semantic, hybrid, or vocabulary-enriched — based on its query type. On LongMemEval_M (Wu et al., 2024), SelRoute achieves Recall@5 of 0.800 with bge-base-en-v1.5 (109M parameters) and 0.786 with bge-small-en-v1.5 (33M par
GitHub
Machine Learning Engineering Open Book. Contribute to stas00/ml-engineering development by creating an account on GitHub.
Scott Alexander · Astral Codex Ten
...
GitHub
Contribute to jxnl/personal-monorepo-template development by creating an account on GitHub.
GitHub
A tiny native macOS to-do list that reveals from your chosen screen corner. - Emanuele-web04/Peekaboo
Ehsan Pajouheshgar1, · cells2pixels.github.io
Explore interactive demos of a self-organizing pattern formation model that combines Neural Cellular Automata with Neural Fields.
AI 2040
A detailed forecast and recommendation for how the US, China and the rest of the world should navigate superintelligence.
Interfaze
A new model architecture for deterministic tasks achieving the highest accuracy, precision and consistency for tasks like OCR, Audio understanding, Structured Data Extraction and more
Shijia Liao · Fish Audio
> - S2.1 Pro, Fish Audio's most advanced voice model, is now available as a free text-to-speech API
GitHub
Toolkit for building native desktop apps. Contribute to vercel-labs/native development by creating an account on GitHub.
hyperframes.heygen.com
Source link only
GitHub
Agent orchestration for GitHub or Linear. Contribute to gannonh/kata-symphony development by creating an account on GitHub.
[Submitted on 17 May 2023 (v1), last revised 3 Dec 2023 (this version, v2)] · arXiv.org
Language models are increasingly being deployed for general problem solving across a wide range of tasks, but are still confined to token-level, left-to-right decision-making processes during inference. This means they can fall short in tasks that require exploration, strategic lookahead, or where initial decisions play a pivotal role. To surmount these challenges, we introduce a new framework for language model inference, Tree of Thoughts (ToT), which generalizes over the popular Chain of Thoug
panav.gitbook.io
Comprehensive robotics guide covering hardware, ROS 2, SLAM, robot learning, and AI - from fundamentals to production systems.
svedit.dev
Selection:
[Submitted on 6 Jul 2026] · arXiv.org
Dense spatial perception is essential for physical intelligence, where visual systems are expected to recover structured, metric, and actionable representations from pixel observations. Modern visual foundation models tend to prioritize semantic invariance, often at the expense of detailed spatial understanding. In this work, we study vision pretraining through a boundary-centric lens, motivated by the premise that boundaries and shape discontinuities offer essential cues for perceiving geometri
GitHub
A curated collection of public industrial datasets. - jonathanwvd/awesome-industrial-datasets
cs231n.github.io
Course materials and notes for Stanford class CS231n: Deep Learning for Computer Vision.
Contributors to Wikimedia projects · Wikimedia Foundation, Inc.
From Wikipedia, the free encyclopedia
WrobotGames · itch.io
Game engine and 3d graphics enthusiast or something like that, I'm not sure.Be sure to follow me on mastodon and Twitter
itch.io
itch.io is a simple way to find, download and distribute indie games online. Whether you're a developer looking to upload your game or just someone looking for something new to play itch.io has you covered.
Jacob Austin · How To Scale Your Model
Training LLMs often feels like alchemy, but understanding and optimizing the performance of your models doesn't have to. This book aims to demystify the science of scaling language models: how TPUs (and GPUs) work and how they communicate with each other, how LLMs run on real hardware, and how to parallelize your models during training and inference so they run efficiently at massive scale. If you've ever wondered "how expensive should this LLM be to train" or "how much memory do I need to serve
Jun Yu Tan · jytan.net
Incrementally optimizing a BPE tokenizer with complexity analysis and benchmarks.
comma.ai
An AI upgrade for your car
comma.ai
An AI upgrade for your car