Neural networks are notoriously hard to debug. augustus odena has developed a new debugging methodology by adapting traditional coverage guided fuzzing techniques to neural networks.

What does a pruned deep neural network "forget"? Very excited to share our recent work w Aaron Courville, Yann Dauphin and @DreFrome weightpruningdamage.github.io

A Novel Technique for Non-Invasive Measurement of Human Blood Component Levels From Fingertip Video Using DNN Based Models ieeexplore.ieee.org/document/93350…

sciencedirect.com/science/articl…

Corrections to “A Novel Technique for Non-Invasive Measurement of Human Blood Component Levels From Fingertip… disq.us/t/3y4fhxr

Use the module and explore new use-cases. Happy parsing. 🙂 pypi.org/project/indicp…

Bangla Unicode Normalizer developed at Bengali.AI GitHub: github.com/mnansary/bnUni… PyPI: pypi.org/project/bnunic…

Grapheme Parser for indic languages. Available languages: Bangla, Malyalam, Tamil, Gujrati, Panjabi, Odiya, Hindi. pypi.org/project/indicp…

This Prediction!😲

2025 update: A Nobel Prize for Plagiarism (Technical Report IDSIA-24-24). Sadly, the 2024 Nobel Prize in Physics awarded to Hopfield & Hinton is effectively a prize for plagiarism. They republished foundational methodologies for artificial neural networks developed by Ivakhnenko,

Why does RL work for enhancing agentic reasoning? This paper studies what actually works when using RL to improve tool-using LLM agents, across three axes: data, algorithm, and reasoning mode. Instead of chasing bigger models or fancy algorithms, the authors find that real,

🤖deepagents: the open source, multi-model agent harness We're releasing 0.2 of deep agents, with a big addition: a "backend" abstraction This lets you swap the filesystem you use from a local filesystem to a remote VM to a database to anything blog: blog.langchain.com/doubling-down-…

MIT researchers propose Recursive Language Models You are going to hear more on this in 2026. Why does it matter? What if LLMs could process inputs 100x longer than their context window? Context length is a hard constraint. You can extend it with architectural changes, but

This paper shows how to make adversarial examples with GANs. No need for a norm ball constraint. They look unperturbed to a human observer but break a model trained to resist large perturbations. arxiv.org/pdf/1805.07894…