AI Intelligence Archive

During Meta's Global AI Developer Hackathon, I spent roughly four intensive days building RAME Code,...

Recent work on robot manipulation has focused on specialist policies trained on demonstrations. We show that generalist AI models can control manipulators more reliably than specialist policies such as vision-language-action models (VLAs) …

Large language models reinvent the wheel all the time. They conflate task-solving with the execution of the solutions, which forces them to solve every problem from scratch. We show that once a task has been reasoned through, the applicati…

We prove that the set $\mathcal{N}_N$ of ReLU networks with one hidden layer and at most $N\in\mathbb N$ neurons is weakly closed in $W^{1,p}(Ω)$, for a bounded connected open set $Ω\subset\mathbb R^d$. Consequently, every coercive, weakly…

Predicting the future motion of multiple people is inherently stochastic: the same observed history admits many plausible continuations depending on intent, coordination, and social context. Yet the dominant paradigm in multi-person 3D mot…

The Gaussian jet of an image is a graded vector space: a dilation by $λ$ multiplies derivatives of order $k$ by $λ^{-k}$. Local graded convolutions are exactly homogeneous differential operators, and a local feature is dilation-invariant i…

Test-time reinforcement learning (TTRL) adapts pretrained language models to unlabeled target-domain data using self-generated pseudo-labels, whose reliability remains poorly understood. We analyze majority-vote supervision for TTRL with o…

Large reasoning models (LRMs) improve task performance by generating longer intermediate reasoning traces, but this substantially increases inference costs and makes low-precision quantization increasingly important. However, aggressively …

Purpose: Surgical operative reports support procedural documentation, surgical training, performance assessment, and workflow review. However, extracting meaningful information often requires extensive manual review and clinical expertise.…

Loco-manipulation, which requires mobile manipulators to coordinate locomotion and manipulation over long horizons, is a key capability for large-object rearrangement in applications such as service robotics and warehouse automation. Despi…

Many multimodal alignment problems require mapping a source modality into a fixed space defined by a target modality, where the target space is not merely an intermediate embedding but is used directly for downstream analysis. In this sett…

Can a sender that only computes hashes, with a language model only at the receiver, transmit short human text more cheaply than a classical sender trained on the same domain? We answer with one pre-registered run on 1,000 English user utte…

In many areas of AI, general-purpose models have increasingly replaced handcrafted methods and specialized architectures. We argue that embodied AI is poised for a similar shift. Our key claim is that embodied tasks can be formulated as in…

This paper describes an approach and use case to estimate the correctness of LLM-generated COBOL summaries without access to human-authored references. The core intuition is that inter-model agreement on semantics is informative about trut…

The pigs were bleeding. That was the point of the experiment: could airway pressure reveal hemorrhage before it became critical? In the UCR Time Series Classification Archive, the de facto benchmark for Time Series Classification (TSC), th…

Radiology AI has developed along two paths: specialized models that perform well on narrow tasks but cover few clinical findings, and generalist models that address a broader range of tasks but remain prone to hallucination and inaccurate …

Reinforcement learning (RL) rewards are notoriously difficult to design and control, often leading to the model learning unintended behaviors such as reward hacking. One potential solution is to monitor for reward hacking and penalize it w…

The key-value (KV) cache dominates memory capacity and bandwidth in long-context LLM serving. While 4-bit microscaling formats (NVFP4, MXFP4) shrink the cache and run attention on FP4 Tensor Cores, a fundamental gap remains between algorit…

The timeline by which quantum computers can solve breakthrough problems in science depends on improved quantum algorithms as much as on better hardware. Such algorithmic advances are typically achieved through many years of expert human co…

Dominant methods for interpreting large models impose strong structural assumptions. Generative Latent Priors (GLP) are a complementary approach: a diffusion model that learns the distribution of a frozen model's activations directly, impo…

Machine learning (ML) methods have been explored as a means of optimizing lattice field theory calculations, with increasing interest in recent years. This chapter gives an introduction and summary to the use of ML methods to optimize latt…

A shared expense tab that learns a group's unwritten rules into Walrus Memory and settles debts in USDC on Sui through Tatum, with x402 payments and an agent bound by a Sui Allowance.

ICYMI AI: The latest AI trends, delivered to Dev.to Tech Talk: Can (and should) AI verify...

AI visibility is becoming a regular reporting line for brands and agencies, but a single prompt run...

The problem Look at almost any CI workflow and you'll find a line like this: - uses:...

Why standard Kubernetes pods fail when AI agents start writing code and how to build a sub-second,...

Claude Code put the account email in the model's context, and the model used it as a User-Agent contact. What the privacy mod checks and what it misses.

In my last speech, I wanted the audience to leave with something they could use beyond a particular...

Want AI to answer in a specific way? Don't just tell it. Show it. In this episode of Prompt Pad,...

This is the third and final part of the series "Your first steps in Computer Vision on AWS". If you...

If you copied an MCP server example in the last year and it stopped working, you are not doing...

## **By Manikanta Marathi** • *Lead Site Reliability Engineer, NexusMemory Project* --- ### The...

Ask a coding agent for "an animated title for our launch" and you usually get a page of animation...

Our order can now wait for an external result without pretending that the operation has already...

The central challenge of working with AI is speed vs. quality. Work too slow and your...

I shipped the first version of GEO Optimizer on February 18, 2026. Eight months later it is at...

The European Commission has preliminarily found that TikTok’s service design may breach the Digital...

AI is automating tasks juniors used to learn from. New hiring and QA research shows why the real challenge is rebuilding the path from beginner to experienced engineer.

A local LLM chat app built on llama.cpp, Node and a hand-built web UI, plus what it took to make localhost secure and ship the same model on Android.

Claude Opus 5.5 failed the same review three runs out of three. Same pull request, same reviewer...