AI Intelligence Archive

Learning transferable representations for dynamic text-attributed graphs (DyTAGs) requires models to capture underlying interaction dynamics that persist across domains. However, existing methods tend to overfit to domain-specific structur…

We propose sliced Orlicz-Wasserstein (SOW) distance which is a generalization of sliced Wasserstein (SW) distance. SOW replaces the $L^p$ norm in SW with a Luxemburg norm cost induced by an Orlicz function $φ$. First, we prove that SOW dis…

Multimodal contrastive learning is a dominant paradigm for learning transferable representations from unlabeled data, but standard objectives primarily capture information that is redundant between modalities. Partial Information Decomposi…

Accurate assessment of Schistosoma japonicum-associated liver fibrosis is essential for disease management and long-term follow-up in endemic regions. Ultrasound provides non-invasive imaging, but complex local echogenic patterns and anato…

Recommender systems rely heavily on heterogeneous behavioral feedback to infer user preference. Although abundant, these signals are imperfect measurements: the same observed behavior can arise from different underlying states, such as gen…

Predicting smooth dynamics and collisions requires modeling continuous evolution and abrupt state changes. We introduce HamiFormer, a dual-expert diffusion field combining whole-window denoising with residual-corrected Hamiltonian propagat…

Ultrasound (US) acquisition depends on the operator's ability to interpret anatomy and anticipate how the view will change with probe motion. Many robotic US navigation methods select actions without explicitly predicting these anatomical …

Radiomap blind prediction aims to infer radiomaps from observable representations of the propagation environment and base station configuration without field measurements. In practice, the observable representations are inherently incomple…

As AI agents are becoming widely adopted in the financial services industry, careful measurement is essential to understand where they can be reliably deployed and where oversight and professional review remain necessary. Such measurement,…

This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...

A trained neural network can be represented by a parameter vector in high dimensions. Learning distributions over these vectors enables the generation of new models across various tasks and architectures. A central challenge is permutation…

Over-the-air computation has emerged as a scalable and efficient solution for deploying federated learning algorithms in wireless networks by exploiting waveform superposition for simultaneous model aggregation. Most existing work struggle…

Unified multimodal models combine understanding, generation, and editing within a single network, offering a promising foundation for versatile multimodal applications. However, growing multimodal contexts make KV cache storage and access …

Flow critics learn return distributions by transporting Gaussian noise to Bellman endpoints via continuous velocity fields. While velocity bootstrapping stabilizes training by querying a successor teacher, existing methods face a structura…

Several works have explored multi-agent reinforcement learning (MARL) in LLM collaboration. However, constructing reliable rewards is difficult in practice, as complete and accurate metrics are often unavailable and hard to aggregate. Pref…

A four-stage LLM pipeline gives up as much as 40.5 accuracy points at its own interfaces (gemma-3-12B on MATH-500, Holm-corrected p = 1.66e-19; the largest tax in the primary family). We hold model, problem, stages, stage prompts and compl…

Model merging efficiently combines specialized large language models (LLMs) without joint retraining, but can substantially alter expert routing in Mixture-of-Experts (MoE) models. Such \emph{routing drift} is often interpreted as routing …

This paper studies learning of shuffle ideals with membership queries as well as with contrastive queries---a form of membership query that reveals not only whether a selected word $w$ is in the target language or not, but also provides a …

Raising the update-to-data (UTD) ratio breaks off-policy critics in two ways grouped as "plasticity loss": collapsing representations and growing value magnitude $|Q|$. We separate them in Soft Actor-Critic (SAC) with scaled critics (width…

Fine-tuning a language model on new data can make it forget facts that it should keep. We ask whether measurements taken at the start of a fine-tuning run can bound, for each protected fact, the probability that the run makes the model for…

This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...

Clinical Large Language Models (LLMs) achieve strong medical-exam accuracy; however, a correct answer does not guarantee that the explanation names the concepts that actually drove the decision. We introduce three lightweight, directly int…

Why adding autonomy to a software problem can make the architecture worse We have started calling...

Last week I got an unsolicited security report about my QR code service. It was polite, it was...

Background I have a LINE Bot that I use every day, linebot-helper-python. If you send it...

A deep dive into why I built EcoPrompt, the peer-reviewed research behind its metrics, and how to track LLM environmental impact locally in your browser.

I want to talk a bit about where we came from in software and where we are now. Not the industry in...

Evaluation is not a new discipline invented for a new kind of system. It is the oldest discipline in...

Most developers still treat prompt injection as a leakage problem. Someone types an adversarial...

Agent runtimes optimize for density and reject when full. That is not scheduling. Three failure modes at capacity, and who gets to call an agent...

LoRA and DoRA explained: matrix shapes, the geometry of weight decomposition, exact memory math for a 27B model, and what the DoRA benchmarks support.

Originally published on my personal...

This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked I built...

The honest constraint behind everything I build is that there is one of me. A portfolio of sites...

I've been building Hexzie (HexTelegram) a Telegram-based AI assistant that goes beyond just sending...

A Claude Code Stop hook that runs your tests every time Claude tries to finish, and sends it back to work when they fail.

Most LLMs are built to generate. Jev is built to decide. That difference sounds small, but it...

Resumo em português: este tutorial mostra como dar a um agente de IA (Claude, Cursor, ChatGPT) acesso...

There's a special kind of stubbornness that leads someone to say "I will generate photorealistic 3D...

TL;DR The exposure problem: AI-driven development pushed exposed credentials to 1.27...