AI Intelligence Archive

Author: Cyrus Wong (黃俊彥) — Google Developer Expert - Cloud (AI), Senior Lecturer at HKIIT When...

Shortly after SQLazy was launched, we offer it to a group of developers to test using their own...

Instagram's Post URL Is a Database Row. Here's What Reverse Engineering It Actually Shows. The...

My samurai's dash slash looked great in the sprite sheet preview. Then I dropped it into Godot, hit...

Exact by Expo compiles one Contract file into native iOS, macOS, web, and Linux views. Here is how it compares to React Native and Electron, and what breaks.

How NCM writes text coarse to fine in 11 steps instead of 128, what the paper claims, what I measured on a laptop, and whether it will replace LLMs.

AI agents are getting good at finding work and agreeing on a price. Paying for that work is where...

Atlassian published its State of Developer Experience 2026 this week, and one number in it stopped...

A while back I hid one sentence inside a log file and handed the file to my coding agent. It ran the...

Diabetic retinopathy (DR) lesions vary widely in shape, and microaneurysms (MAs) span only a few pixels. We hypothesize that modeling the spatial organization of lesion regions, with global context and shape-adaptive scanning, improves the…

We propose a novel conditional entropy function as a basis for quantifying predictive uncertainty in Evidential Deep Learning (EDL) for glaucoma detection from retinal fundus images. Using the EyePACS-AIROGS-light-V2 and RIM-ONE-DL dataset…

Nepali speakers regularly mix English words into conversation, but multilingual speech recognisers often struggle with language switches and the writing script used for English words. We study how to adapt SraVaani, a 449M-parameter hybrid…

Remote sensing imagery acquired by Unmanned Aerial Vehicles (UAVs) supports wide range of applications; however, deploying machine learning (ML) models on resource-constrained aerial platforms introduces challenges beyond predictive accura…

"It learns over time" is the most common claim made about AI agents with memory, and the hardest one...

Small language models (SLMs) running on mobile devices can keep user data private and work without connectivity. But they perform well only when fine-tuned for the target task and sized for the target device, a process that today requires …

This question came up in Chinese AI developer circles recently, sparked by a talk Wang Jian gave at...

SDR-to-HDR reconstruction is an ill-posed problem in which clipped highlights, crushed shadows, and quantization artifacts must be recovered while preserving the original content. Latent diffusion models provide powerful generative priors …

Keeping the same URLs during a website migration is valuable, but it is not a guarantee that organic...

Compositional generalization is an important form of out-of-distribution generalization, defined as the ability to train on some combinations of modules (e.g., functions such as sort, filter) and then generalize to unseen combinations. Des…

Open-Vocabulary Scene Graph Generation (OV-SGG) requires models to recognize visual relationships beyond the training vocabulary, yet existing methods often rely on dataset-specific object--predicate co-occurrence patterns. Under long-tail…

Simulation optimization typically returns a single estimated optimal point. When decisions also depend on criteria evaluated independently of simulation, such as resource cost, the decision maker instead needs the set of designs whose expe…

Author: Cyrus Wong (黃俊彥) — Google Developer Expert - Cloud (AI), Senior Lecturer at HKIIT ...

Existing Chinese educational corpora often suffer from fragmented coverage and a lack of systematic organization. In this paper, we propose WoW (\textbf{Wo}rld Kno\textbf{w}ledge), a large-scale dataset designed for the full-cycle training…

Judge an AI testing tool by what survives a manual check, not by how many bugs it reports. I build...

Reliable inference for rankings of large language models based on human pairwise comparisons must preserve the privacy of individual preference records. To meet this need, we develop methods for score and rank inference under the Bradley-T…

KL-regularized reinforcement learning, the objective behind maximum-entropy RL and RL from human feedback, is variational inference in the graphical model of "control as inference": the regularized optimal policy is a posterior over trajec…

Integrating human feedback into language models has gained increasing attention as a means to align model outputs with human preferences, with Reinforcement Learning from Human Feedback (RLHF) serving as a prominent framework for preferenc…

A residential solar installer — 22,000 accounts across three states — found this one in a state...

As AI agents become increasingly capable, users must still recognize when and how to ask for help, leaving many opportunities for useful support unrealized. Proactive agents hold the promise to close this gap, but effective proactivity req…

As AI-based products permeate society, specifically systems using generative models, a belief system is emerging about what these products are and what they can and cannot do. One common belief concerns the perception of the form of langua…

We introduce SafeRoute-MAS, a coverage-aware, risk-calibrated procedure that keeps all specialist messages or removes one using only pre-integration information. On a sealed cache of 5,328 committees, its source-compatible operating point …

Analog integrated circuit (IC) design is a multi-turn, simulator-grounded engineering task that demands iterative reasoning over coupled performance tradeoffs, yet proprietary process design kits (PDKs) make hosted large language model wor…

Active learning aims to reduce annotation cost by selecting the most informative examples for labeling. In the low-budget regime, where uncertainty-based methods often fail, coverage-based active learning methods such as ProbCover have bee…

Parallel drafters accelerate LLM decoding by proposing a whole block of draft tokens in a single forward pass, making them attractive for LLM serving. Recent systems optimize goodput (i.e., accepted tokens per second) because rejected draf…

Most language models deployed outside the United States and China are fine-tuned descendants of a small number of pretrained families. We argue that fine-tuning leaves the decisive properties of a model inherited from its base: vocabulary,…

You kick off three agents on the Mac at home, then head to the office. Somewhere on the way one of...

Why Soulcast pull requests and zero-shot roadmaps collapse when requirements shift—and why the engineering journey still matters.

How I built a JavaScript visualizer by instructing Claude Code in plain language, including what I got wrong, how I checked the work, and where this approach falls short.

Bob Smith wrote an article on agent memory that argues for an append-only log with a projected view...

n8n is set to demonstrate agent-driven workflows built with Microsoft technology at Microsoft Ignite...