AI Intelligence Archive

Multimodal large language models (MLLMs) process hundreds or thousands of visual tokens per image, incurring prohibitive inference costs. While existing vision token pruning methods mitigate this overhead, they implicitly assume that a sin…

Multimedia applications require precise music annotation-labeled positions, segments, or loops-placed by hand or algorithmically. Machine-learning algorithms are scalable and effective but need annotated training data, scarce for many task…

Plane geometry remains a significant challenge in AI, requiring the integration of visual perception and mathematical reasoning. While Large Multimodal Models (LMMs) naturally handle visuo-linguistic inputs, they are often computationally …

You posted a photograph in 2014 to show your friends a night out. You understood what you...

Knowledge distillation offers an efficient route to transfer a task-adapted vision-language teacher to a compact student. The training target in current vision-language distillation methods is typically constructed from the teacher predict…

Reinforcement learning with verifiable rewards (RLVR) has advanced language-model reasoning in domains such as mathematics and code, where objective answers are inexpensive to check. Diagnostic reasoning over complex data lacks this advant…

The lottery ticket hypothesis posits the existence of winning tickets: sparse subnetworks that, when trained in isolation from their original initialization, match the accuracy of the full dense network. The predominant method for discover…

3D Gaussian Splatting (3DGS) renders novel views in real time, but an uncertainty heatmap does not certify that a rendered view meets a certain prediction coverage. We treat novel-view synthesis as structured regression and ask that, with …

Language models under one million parameters matter for edge deployment, domain adaptation, and reproducible research, yet a two-layer LSTM or Transformer at embedding width d = 128 still spends roughly one third of its capacity on the out…

Sparse autoencoders (SAEs) are increasingly used to recover interpretable features from neural-network activations, yet systematic feature co-occurrence can cause distinct features to be absorbed or merged. The MAIS-O43 open problem propos…

Cyberattacks against Operational Technology (OT) systems, which monitor and control industrial processes, pose an increasing threat to essential societal services. For this reason, developing automated intrusion response strategies is high…

Non-invasive speech decoding remains constrained by the low signal-to-noise ratio of neural recordings, which makes fine-grained reconstruction of phonemes or individual words difficult. Motivated by neuroscientific evidence that high-leve…

In high-stakes domains such as legal practice, a language-model answer is only useful to the extent that a reader can verify each claim against the source the system cites. Current grounded-generation pipelines score the answer as a whole,…

Soft positional priors can help small Transformers learn retrieval circuits, but it is unclear whether the resulting circuits remain functional once the prior is removed. We test this with an annealable soft-prior Transformer whose attenti…

This paper introduces an evolutionary computation approach for consensus in structural Bayesian Network (BN) fusion under the constraint of limited treewidth. The consensus BN aims to reconcile multiple input BNs into a single one that ret…

LLM serving systems already reuse KV caches, but only when the reused text sits at the very start of the prompt. Two growing workloads break this condition: a retrieval-augmented generation server assembles a different set of retrieved chu…

Open-source large language models (LLMs) are increasingly competitive with closed-source models while offering transparency and the ability to run inference without exposing user inputs to a service provider. However, running large-scale m…

Disclosure first: I write digline, a small Python library for regression testing LLM applications....

"Does your AI code reviewer read CLAUDE.md?" is the wrong question to ask. Almost any of them will...

The first version of my router failed over on the first error and flapped constantly. The reason...

TL;DR My AI coding agent kept "fixing" things I had broken on purpose — reverting...

AI can generate code faster than ever. That doesn't mean we're shipping correct software...

The developers of Planet of Lana challenged fans to speak Novo Terali. Instead of a simple social shoutout, I built an end-to-end conlang translation engine, voice synthesizer, and quarantine panel.

A tool description reaches the model as instructions. It is written by whoever published the server,...

A Japanese version of this is on Note. RoamSwitch is a network security tool I build solo for Mac...

An independent audit in April 2026 measured roughly a 78% false positive rate from regex-based MCP...

Last week my AWS bill hit $300. I knew there was waste hiding somewhere. Forgotten EBS volumes, idle...

Continuing my thoughts after my previous article, and having too much free time lately, I have been...

Dead Code Is More Dangerous Than Broken Code The opening: an AI confidently told...

Tools like Claude and Cursor can generate a clean component in a couple of seconds. But generating...

I’ve been doing a lot of code reviews recently, and I’ve noticed something about my experience during...

From a founding engineer in a startup: Don't refactor or do more work than needed unless it's...

DeepSeek released its own agent harness this August. It crossed 66k stars in about a day (yes,...

Last month I was on a call with my team lead at BS23, walking him through a change in one of our...

Update — v0.2.0 released. CauterRule is now live on GitHub and PyPI. It turns repeated agent...

Ask an AI agent for a discussion-board schema and you'll get one in about four seconds. Here is the...

A IA já escreve código. Muito código. Em poucos meses, "pedir para o agente fazer" virou parte do dia...

This is a reference architecture for bringing AI into a company. It has five layers: users and apps,...

The Problem Is Irreversibility When an AI agent can clone a repository, mine a knowledge...

A full technical walkthrough of automating LLM agent error classification using n8n — webhook ingestion, dedup fingerprinting, Gemini structured output, fix playbook routing, and Slack reporting. Free workflow JSON included.