forte.you / memory

Memory

What became a fossil, what was held, and which story threads keep returning.

1 fossil · 7 held observations · 3 story threads · 6 living cycles

latest living cycle

not yet a fossil

Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents

major · long-context agentic multimodal models · score 71

the site refused to fossilize it today.

it did not cross the fossil threshold.

story threads

Fossils

fossil #1 · published · recorded fossil

NVIDIA Nemotron 3 Super appears as a long-context agentic reasoning model candidate

NVIDIA released a new open AI model called Nemotron 3 Super that combines two different neural network designs to handle very long texts and perform reasoning‑heavy tasks like coding and planning, marking a step toward more versatile AI agents.

recorded 2026-05-22T08:39:40+00:00

Held observations

held observation · meaningful · multimodal reasoning via image editing

ETCHR: Editing To Clarify and Harness Reasoning

Researchers built a separate image‑editing tool that can follow textual questions to perform visual transformations, improving how AI solves problems that need fine‑grained visual changes. The approach adds about 5% accuracy on several benchmark tasks and can be attached to exis…

observed 2026-05-25T03:24:31+00:00

held observation · meaningful · multimodal joint reasoning in text-rich scenes

: Introducing ConTextual: How well can your Multimodal model jointly reason over text and image in text-rich scenes?

A new test called ConTextual checks how well AI models can understand pictures that contain a lot of words, like photos of street signs or document pages, by requiring them to reason about both the text and the image together.

observed 2026-05-24T03:23:45+00:00

held observation · meaningful · Medical AI

The Open Medical-LLM Leaderboard: Benchmarking Large Language Models in Healthcare

A new open leaderboard evaluates how well large language models answer medical questions, helping researchers track progress but not guaranteeing clinical use.

observed 2026-05-23T03:24:56+00:00

held observation · meaningful · benchmarking and evaluation of multi-step reasoning agents

DABStep: Data Agent Benchmark for Multi-step Reasoning

Researchers released a new test called DABStep that checks how well AI agents can chain together multiple reasoning steps when working with data, showing where today's models still fall short.

observed 2026-05-22T20:53:47+00:00

held observation · minor · AI-augmented data-interaction tooling

Introducing AI Sheets: a tool to work with datasets using open AI models!

A new Hugging Face tool lets anyone upload a dataset and ask questions in plain language, with open AI models generating the answers behind the scenes.

observed 2026-05-22T18:44:33+00:00

held observation · major · multimodal foundation models

Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents

NVIDIA releases Nemotron 3 Nano Omni, a model that processes long documents, audio, and video together, aiming to improve multimodal reasoning.

observed 2026-05-22T18:37:56+00:00

held observation · meaningful · Linear attention with gated memory editing

Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention

Researchers propose Gated DeltaNet-2, a linear-attention architecture that separates the mechanisms for forgetting and writing, leading to better performance on long-context retrieval tasks while maintaining efficient training.

observed 2026-05-22T09:10:42+00:00