The Archive

Computational reproducibility remains difficult despite being central to scientific research. In this paper, we show how the international FABRIC testbed, combined with large language model (LLM) coding assistants through LoomAI, can simplify reproducing published experiments across multiple domains. We reproduced three case studies on FABRIC, covering BBR-family congestion-control evaluations, LAMMPS molecular dynamics scaling benchmarks on a CPU-only MPI cluster, and stress protein homeostasis genomics pipelines. Rather than focusing only on matching numerical outputs, we evaluate whether t...

How can we generate high-quality relevance annotations at scale without the cost and delays of human labeling? Relevance annotations are the backbone of search ranking systems which is needed for training data preparation, NDCG evaluation, and root cause analysis. However, human annotation is slow and off-the-shelf LLMs suffer from accuracy on domain-specific tasks. We propose a calibrated model cascade, a systematic approach for cost-efficient offline relevance annotation by routing queries through progressively larger fine-tuned classifiers. Our central insight is that accuracy and cost are...

Federated learning is vulnerable to backdoor attacks in which malicious clients inject poisoned updates while preserving benign-task performance. In this paper, we study a semantics-driven backdoor mechanism in which attackers use natural visual accessories as triggers and manipulate only the trigger color while keeping the attack pipeline fixed. Our framework considers semantic trigger objects such as masks and sunglasses, instantiated in black and white variants, and evaluates their effect in a controlled federated learning setting. Malicious clients construct poisoned samples by applying a...

Group-based reinforcement learning effectively post-trains LLM agents for long-horizon, sparse-reward tasks by deriving step-level credit from trajectory outcomes. However, this ties a step's credit to its rollout's final outcome: semantically near-identical intermediate steps receive opposite credit depending on whether their trajectory eventually succeeded or failed. Such semantic credit inconsistency sends conflicting gradients to similar actions and wastes the partially-correct progress inside failed rollouts. Motivated by this, we propose Semantic Consistency Policy Optimization (SCPO), ...

Production vision pipelines silently degrade on blurry input, wasting compute on downstream OCR, retrieval, and vision-language model (VLM) calls that cannot recover a usable output. We present MagikaDocumentFromPixel, a lightweight, CPU-friendly image quality gate that classifies a single image as sharp, blurred, or uncertain in roughly 7 ms on a single CPU core. The contributions are (i) a recipe selected from a 46-configuration, 8-sweep empirical search that isolates input resolution as the dominant lever and shows architecture capacity only pays off at >= 384 px; (ii) a confidence-aware r...

To better assist users with completing challenging tasks, AI agents mediate communications, access data, and interact with different APIs. Many employers (and even nation-states) already provide their users with this technology. However, widespread adoption of AI agents creates a new risk to abuse access to user data for another goal: surveilling users. These users might not even have the ability or permission to control the actions and data accesses of the surveilling agents. We introduce and formalize the problem of agentic surveillance: the ability of an AI agent to analyze available infor...

Achieving strong optimization generalization across diverse optimization problems while requiring limited training resources remains a challenging problem for optimization-oriented large language models (LLMs). Existing approaches typically rely on large-scale supervised datasets, costly reasoning annotations, and expensive intermediate step verification, resulting in substantial training overhead. To address these challenges, we propose MiniOpt, a reinforcement learning framework that learns to solve optimization problems through an "reasoning-to-model-and-solve" paradigm. MiniOpt decomposes...

Sparse Mixture-of-Experts (MoE) architectures have emerged as an increasingly influential paradigm as they offer a strategic balance between parameter scalability and computational efficiency. However, low-resource languages, which suffer from a scarcity of high-quality training data, often have their tokens routed to different experts than those predominantly activated by high-resource inputs, which limits cross-lingual expert sharing. This cross-lingual routing divergence consequently hinders their efficacy in multilingual contexts. To address this issue, we propose SARA (Semantically Ancho...

Large language models are increasingly deployed as agents that solve tasks by interacting with external tool environments. Although recent tool-use benchmarks increasingly cover complex task settings, they still largely assume clean, stable, and trustworthy tool environments, leaving tool-environment unreliability insufficiently examined. We introduce ToolBench-X, a benchmark for evaluating agents under recoverable reliability hazards. ToolBench-X contains executable multi-step tasks across diverse domains and sequential, parallel, and mixed workflows, each paired with deterministic tools and...

Commodity futures can be represented hierarchically, with underlying assets at the upper level and individual futures contracts at the lower level. Entities at each level can be connected by edges reflecting inherent correlations, with cross-level edges capturing contract-to-underlying asset connections. Building on our observations of these structures, we propose a hierarchical graph learning approach for calendar spread (CS) strategies in commodity futures markets, addressing two significant gaps in the machine-learning literature: (i) the absence of learning-based methods for CS strategies...

The Speaker comes in four colors… but red is the way. | Photo: David Pierce / The Verge Right out of the box, the new Google Home Speaker passed a couple of important tests. Even with the volume at 100 percent and music blaring out of the speaker, it quickly ducked the audio and listened every time I said "Hey, Google." In fact, in two days of testing, the speaker's three microphones haven't missed a single wake word - except for the time I stage-whispered to it from the other room while trying to avoid waking up the baby, but I'm not sure that's a fair test. I set up the speaker in the bathr...

AI is booming. New use cases are emerging each day. To capitalize on the technology’s potential, enterprises require data at scale. In many cases, though, the relevant information is blocked or unstructured, which limits its use by AI models. To understand this challenge, consider the foundation of the web itself. The web was not designed…

My experience and reflections on vibe coding an app that I plan on actually using regularly.

Claude finally gets a Slackbot upgrade

OpenAI and Broadcom introduce Jalapeño, a custom AI chip built for LLM inference to improve performance, efficiency, and scale across AI systems.

Cohere partners with Aston Martin Aramco Formula One™ as official Generative AI provider, bringing enterprise AI solutions to enhance performance and innovation across the racing team. Starting Australian GP 2026.

The all-cash deal gives MoEngage access to technology that assigns AI agents to individual customers.

A new update for Google Home could make it less likely your smart home cameras mistake you for someone else, just because you're facing away from the camera. Starting June 23rd, Google's expanding its facial recognition feature so that people you've tagged in your Familiar Faces library can continue to be identified when their faces aren't clearly visible, using "additional non-biometric signals (body size, clothing color, etc.)." The Familiar Faces library will also begin automatically updating with the most recent images of everyone in your house, so you should get fewer inaccurate notifica...

Netflix, A24, Focus Features, and Warner Bros.' Clockwork have all reportedly decided to pass on picking up Artificial - director Luca Guadagnino's new biographical drama about OpenAI cofounder / CEO Sam Altman - for distribution deals. And while Neon and Mubi are still said to be interested in the film, this situation makes it seem like Hollywood no longer has the courage to tell critical stories about Big Tech. Postproduction on Artificial was nearly finished when Amazon MGM unexpectedly announced last week that it no longer plans to distribute the film. The news came as a surprise given ho...

Release: datasette 1.0a35 I'll write more about this one tomorrow, but it's a big release. Three highlights from the release notes: New "Create table" interface in the database actions menu, backed by the /<database>/-/create JSON API . It can define columns, primary keys, custom column types, NOT NULL constraints, literal defaults, expression defaults and single-column foreign keys. ( #2787 ) New "Alter table" table action and /<database>/<table>/-/alter JSON API for changing existing tables: add, rename, reorder and drop columns; change column types, defaults, NOT NULL constraints, primary ...

Oracle is spending billions on data center infrastructure to support AI.

Tool: OPFS + Pyodide test harness I've been pondering if Datasette Lite - the Python Datasette application run entirely in the browser using Pyodide and WebAssembly - might be able to edit persistent SQLite files stored on the user's computer. That's what OFPS (Origin Private File System) is for, so I had Claude Code for web build me this playground UI to try it out in different browsers. Tags: browsers , pyodide , datasette-lite

Vision-language-action (VLA) models can learn manipulation skills from demonstrations, but their capabilities are bounded by the skills in the training data. We present InSight, a framework that unlocks autonomous skill acquisition by rendering VLAs steerable at the primitive-action level (e.g., "move gripper to the bowl", "lift upward", "pour the bottle"). InSight consists of two primary stages: (1) an automated segmentation pipeline that partitions demonstrations into labeled primitives via VLM plan decomposition and end-effector poses to enable VLA primitive steerability, and (2) a VLM-gui...

We study the last iterate of the stochastic subgradient method for one-dimensional convex Lipschitz objectives. For a fixed horizon $n$, we consider the standard fixed stepsizes $η=Θ(1/\sqrt n)$. We prove that, for such stepsize policies, under additive i.i.d. subgradient noise with uniformly bounded variance, the last iterate features an optimization error of order $1/\sqrt n$, thereby removing the extra $(\log n)$ factor present in existing generic bounds. On the other hand, we show that without the i.i.d. assumption, the optimization error can be of order $(\log n)/\sqrt n$. Thus, under th...

Sparse voxel representation has emerged as a scalable foundation for image-to-3D Gaussian Splatting (3DGS) generation, yet current methods struggle to preserve high-frequency visual details of input images due to two structural bottlenecks. First, they adopt discriminative 2D features optimized for semantic abstraction to construct sparse voxel latents, which suppress reconstructive cues and induce a representation bottleneck. Second, in the generation stage, standard diffusion transformers lack effective mechanisms to align dense 2D image tokens with sparse 3D voxel latents, resulting in a c...

Agentic language models dramatically expand the applications of AI yet little is publicly known about how to curate training data for broadly capable agents. Existing open efforts such as SWE-Smith, SERA, and Nemotron-Terminal typically target a single benchmark, leaving open the question of how to train models that generalize across diverse agentic tasks. The OpenThoughts-Agent (OT-Agent) project addresses this gap with a fully open data curation pipeline for training agentic models. We conduct more than 100 controlled ablation experiments to systematically investigate each stage of the pipe...

Artificial intelligence (AI) can enhance what people who use augmentative and alternative communication (AAC) are able to do with their systems. However, evaluating AI-powered AAC interfaces can be difficult. People are intersectional beings and current evaluation metrics can struggle to capture the multifaceted and nuanced desires people may have for their AAC. We explore the complicated nature of six AAC problem spaces, explore how AI might be used in these spaces, and suggest more robust methods of evaluation that take the intersectional nuances of people into account. We also discuss broa...

Fourier Neural Operators (FNO) learn solution operators of partial differential equations by parameterizing global convolutions in the complex Fourier domain. For real-valued PDE solutions, the complex FFT carries representational redundancy through conjugate symmetry. We introduce the Hartley Neural Operator (HNO), the exact real-valued mirror of FNO: it replaces the FFT with the purely real Discrete Hartley Transform and learns a single real multiplier per retained spectral mode, with no complex arithmetic. Because the real Hartley spectrum is not halved by conjugate symmetry, HNO retains t...

Unified multi-modal large language models (MLLMs) have achieved strong text-to-image generation quality, but still struggle with structure-aware prompt following, where object counts, spatial relations, attribute bindings, and coarse layouts must be preserved. We attribute this limitation in part to the entanglement of structural planning and appearance rendering within a single conditioning stream. To address this issue, we propose Implicit Visual Chain-of-Thought (IV-CoT), a latent visual reasoning framework for query-conditioned image generation. IV-CoT decomposes the visual conditioning q...