AI Intelligence Archive

For a decade, progress in artificial intelligence has been measured by how much a machine can do on its own. Large foundation models now write code and run multistep tasks, and personal agents act on a person's behalf. Yet people still for…

Direct Nash Optimization (DNO) aligns a language model to a general preference function by approximating the Nash equilibrium of a two-player preference game. Its practical variant, DNO-Prct, iterates on-policy sampling, LLM-based rating o…

Inverse kinematics (IK) converts end-effector pose commands into joint motion, and many vision-language-action (VLA) policies rely on it to act on a given arm and to transfer across embodiments. Precise IK remains laborious: redundancy and…

Imitation learning policies in robotics are trained on datasets collected through costly real-world teleoperation. Often, the data-collection process is unguided, relying on the teleoperator's intuition, resulting in data that contributes …

Undesired model behaviors can emerge or re-emerge at any stage of training. Once observed, how effectively can we suppress them? To study this question, we first construct two model organisms--language models deliberately trained to exhibi…

When a language model answers, we can usually only estimate why. We build a transformer in which every step is a Born measurement - attention $|\langle q|k\rangle|^4$ normalised over each row, a measured product in place of the feed-forwar…

Given a class of machine learning models and sample access to a data distribution with binary labels, which computational task is harder: training a discriminative model that distinguishes positive and negative labels as well as the best m…

Speculative decoding has been treated purely as a systems optimization that speeds up large language model decoding without changing the model behavior. Under this view, the growing effort to train better draft models has been focused sole…

In-context learning (ICL) lets a pretrained language model perform a task specified by demonstrations in its prompt, with no parameter updates. With arbitrary labels the model must acquire a mapping it cannot have memorized, so the learnin…

Machine learning models in radiotherapy are commissioned by testing them on cases with known answers, which may not reveal a shortcut that the test cases share with the training data. Frontier language models have recently been reported to…

Medical physicists turn a prescription into a delivered dose and check one another's calculations, because one error in a beam calibration or a monitor-unit (MU) calculation can affect every patient treated with it. MedPhysBench has ten se…

Efficient preconditioning plays an important role in large-scale first-order optimization. In this paper, we propose an adaptive accelerated optimistic dual averaging ($\text{A}^2$ODA) method for unconstrained convex optimization that adop…

We study context-aware time-series forecasting, in which a single target variable is predicted from its own history and a set of contextual variables, such as weather and calendar information. As the context becomes more diverse, a single …

Teleoperation remains the default way to collect robot demonstrations, but every episode costs robot and operator time, and every new task starts from scratch. We ask whether a coding agent can take over the teleoperator's job. In our Data…

In LLM-based recommendation, memory acts as a user-level agent in a memory-augmented backbone. Yet users and items remain asymmetric: only the user is given a structured profile; it enters a bandwidth-limited reranker prompt; and it is fro…

Skill memories encode past experiences as textual prompts to improve reinforcement learning (RL) for self-evolving agents. Complementing RL, On-Policy Self-Distillation (OPSD) provides dense, fine-grained supervision to internalize knowled…

Quantifying selection effects in gravitational-wave population studies requires millions of costly signal-to-noise ratio (SNR) calculations. We present $Φ$asmaNet, a compact neural architecture for structured tabular regression, with stage…

Later tokens are costlier to generate than earlier tokens. On frontier open weight models, the disparity in cost may rise to as much as 7x. Through frequent compaction, we show across a broad range of long-horizon and long-input tasks that…

Looped transformers are a parameter-efficient alternative to standard transformers for language modeling. By reapplying the same layers across multiple loop steps, recent looped language models match the performance of non-looped models se…

Talk time with partners rose by a third to 80%, depending on how you count. Only one of the nine...

My old agent skill was one long file and it told every agent I used to run MinIO for local S3. Then...

技能：https://github.com/google-gemini/gemini-skills/tree/main/skills/gemini-api-cli CLI：https://github.com/google-gemini/gemini-api-cli

Qwen gained reported math accuracy after a targeted loop repair. The actual prompt shows Python and practice feedback; smaller Gemma found no established gain.

If you have ever watched an autonomous computer-use agent work through a desktop operating system,...

GitHub: https://github.com/ESeungJun/droidlens Installers for macOS, Windows and Linux are on the...

Most AI memory systems today come down to the same recipe. Split text into chunks, turn each chunk...

Scaling content across countries has long created a tension between consistency and relevance. AI can...

What if you had an entire team of AI agents researching stocks for you? Imagine one agent analyzing...

I built an MCP server that pulls my Oura Ring data into Claude Desktop. It's a small Python project...

TL;DR Code is being written three times faster than anyone can review it: GitHub logged...

One harness, same conditions, four dimensions, and the raw receipts of every call — this round, seven...

If you've ever tried to parse an LLM response in code, you know the pain: the format changes slightly...

At MCP Dev Summit Toronto, Accenture's Michael Forrester told a story about an employee who wanted...

What racking wine teaches about agent memory The mead's lees on October 21, with the racking cane...

Back in September I published Stop bloating your AGENTS.md: reference your conventions instead of...

When an application sends requests to more than one AI model, keeping those integrations organized...

If you give an AI a vague prompt, it will give you a confident answer. And that confidence will cost...

The most common complaint about AI photo editing is not quality. It's "that's not me anymore". You...

Background I have a primary LINE Bot that I use heavily every day:...

Recap In the previous post "Comprehensive Analysis of Managed Agents API", I created an...