The Archive

Provided in both Safetensors and GGUFs. Safetensors, llmfan46/Gemma-4-Harmonia-31B-it-uncensored-heretic: [https://huggingface.co/llmfan46/Gemma-4-Harmonia-31B-uncensored-heretic](https://huggingface.co/llmfan46/Gemma-4-Harmonia-31B-uncensored-heretic) GGUFs…

Explore OpenAI’s Frontier Governance Framework and how our AI safety, security, and risk practices align with emerging EU and California regulations.

We're opening a new office in Milan, our sixth in Europe.

Functional music applications, from consumer focus and sleep aids to clinical interventions, share a distinctive recommendation problem: success is defined by the listener's affective state, but online experimentation on emotion is ethically constrained, particularly for…

Agentic AI systems capable of autonomous planning and extended environmental interaction pose a fundamental control problem: how can humans maintain meaningful oversight of systems that may exceed their own capabilities? Existing approaches to scalable oversight rely on complex…

On-policy self-distillation (SD) improves LLM reasoning by using teacher-side privileged information (PI) to turn sparse verifier outcomes into dense token-level supervision. Existing methods usually assume trusted PI, such as reference answers or successful traces. We ask…

In the era of autonomous agents, machine-actionable data is critical for data-driven workflows. For more than a decade, semantic metadata like schema.org has anchored the FAIR principles (Findable, Accessible, Interoperable, and Reusable) for machine-actionable data and enabled…

Many real-world classification tasks require predicting multiple labels per instance, necessitating the optimization of complex evaluation metrics such as the $F$-measure and Jaccard index. While the Empirical Utility Maximization (EUM) framework is natural for these…

Tabular data in knowledge-rich domains often carries a latent prior in the form of Boolean implication relationships (BIRs) between pairs of features. We mine such relationships with a sparse-exception binomial test. The mined implications form a typed directed graph…

Robustness of neural networks is commonly quantified via local or global Lipschitz constants. However, Lipschitz continuity can be overly coarse or overly restrictive as global robustness measure, failing to capture nuanced, data-dependent behavior. We propose a data-driven…

Modern datacenter RDMA is bottlenecked at the network interface, not the wire. A NIC running RoCE or InfiniBand holds per-connection state for every (application, remote-endpoint) pair - hundreds of megabytes at 1024-application fanout - and pays a four-traversal PCIe round…

Most existing expressivity theories for neural networks assume exact real arithmetic, whereas practical neural networks are executed under finite-precision floating-point arithmetic with implementation-dependent execution semantics. Recent works have begun studying the…

Many applications in quantum simulation, quantum chemistry, and quantum machine learning require not a single quantum state but an ensemble of states characterizing the heterogeneity of a target system. Preparing such ensembles state-by-state is prohibitive in both variational…

NY-12 congressional candidate Alex Bores speaks during a campaign event. | Bloomberg via Getty Images By the time that the Democratic primary for New York's 12th congressional district wraps up in June, Anthropic and OpenAI will have spent millions on their battle over the…

Quick story: I kept losing context every time I had to \`git stash\` and switch branches to test something an agent had suggested. Then I actually read up on \`git worktree\` and it solved the whole problem. What my setup looks like now: \- Main worktree: where I review and…

TL;DR Some AI behavior reminded me of ADHD/Trauma Response (thought loops, task paralysis...) and I laughed it off at first. Then I treated it like my neurodivergent friends: give em some slack. And just like that, the thought loops stopped, response was fast, the answers…

Large language model (LLM) agents rely on reusable skills to solve complex tasks. However, existing skill creation approaches treat skills as isolated and static artifacts, limiting their reusability, reliability, and long-term improvement. We propose MUSE-Autoskill Agent…

Recent advances in agentic systems increasingly treat code as an executable operational substrate rather than as a disposable output artifact. Prior work such as \emph{Code as Agent Harness} frames validated agent-generated artifacts as runtime entities that can be created…

Charts effectively convey quantitative information, but the underlying data are often locked in image form, hindering reuse and analysis. Manually digitizing charts is time-consuming and error-prone, motivating automatic chart-to-table extraction. Recent approaches use…

Predicting the effect of interventions with many possible variations, e.g., therapeutic content that affects mental health outcomes or an earnings call transcript that drives movement in share price, is useful across several domains. However, classical causal estimators tend to…

Symbolic regression (SR) seeks closed-form mathematical expressions that fit observed data. Neural SR methods amortize the search by training an encoder to map observations directly to expressions in a single pass, but this amortized inference leaves a residual amortization gap…

Annotation quality is difficult to sustain when campaigns span weeks or months with small annotator pools. We present a Setswana sentiment dataset of 3,565 tweets annotated by three native-speaker annotators across eight batches and examine why inter-annotator agreement (IAA)…

We adapt Microsoft's QuantumKatas -- a well-established quantum computing curriculum -- from Q# to Qiskit, the most widely-adopted quantum computing framework, and package it with an evaluation framework for systematic LLM assessment. The resulting benchmark comprises 350 tasks…

I know this topic is discussed here a lot but I SWEAR TO FUCKING GOD if I read another "That is real" OR "That is not nothing" OR "That is not X but Y" I am going to have a fucking aneurysm. Yes I have specifically forbidden it from telling me these phrases, yes I have…

This study examines the relationship between speech representations and the hierarchical structure of cognitive assessment in mild cognitive impairment. Utilizing 5,754 German neuropsychological assessment recordings, we evaluate six cognitive tasks across three score levels…

A year ago, generating a polished document as HTML instead of a PPT or a Word file was a fun idea with too many practical problems. Lately I've noticed every one of those blockers either gone or close to gone, and I've quietly stopped reaching for Office on a bunch of…

Hi everyone, I set up a Claude Project a few weeks ago, but the status indicator in the top right corner has never changed from "Indexing" and still shows that little black dot. Does this status ever clear up once processing finishes? Also, my larger PDFs aren't showing…

Neuronal Stochastic Attention Circuit for uncertainty in continuous-time representation learning using C.elegans-inspired circuits.

Neural operator surrogates for Bayesian inverse design in CFD to accelerate MCMC sampling for aerodynamic geometry inference.