arXiv:2608.27662v1 Announce Type: new Abstract: This work presents a generative continual learning framework based on growing self-organizing maps (GSOMs) that are augmented with learned distributional statistics as well as encoder-decoder models for class-incremental learning. The proposed approach enables exemplar-free replay using distributional statistical memory, which eliminates the need to store raw data. Each GSOM unit maintains its own mean, variance, and covariance estimates, which are subsequently used to generate synthetic samples for replay; in encoder-decoder configurations, these samples are then decoded back into the input space (via ancestral sampling) for subsequent training. Our method is fully unsupervised, as it does not rely on explicit task boundaries or class label…

arXiv:2608.27651v1 Announce Type: new Abstract: Unsupervised representational alignment recovers a stimulus-by-stimulus correspondence from geometry alone, but the automorphism group of the stimulus geometry bounds what any such alignment can identify, before data exist. The obvious diagnostic for this degeneracy, the cheapest non-identity relabelling, ranks two published designs in the wrong order, because dense sampling creates near-duplicates whose transposition is nearly free. We turn this known invariance (Demetci et al., 2024) into a design-time diagnostic and intervention. In colour, where candidate geometries have closed form, we show that the failure is structural: sixty-four times the restart budget leaves a symmetric design unmoved while an asymmetric set at the same N recovers…

arXiv:2608.27634v1 Announce Type: new Abstract: Nearest neighbor classification relies fundamentally on how locality is defined, yet conventional $k$-NN imposes the same neighborhood cardinality throughout the feature space. This assumption can be inadequate for data whose local geometry varies substantially across the underlying manifold. We introduce Curvature-Aware Radius Shrinkage for Adaptive Nearest Neighbor Classification (CARSANN), a geometry-driven framework that adapts the spatial support of each neighborhood according to local geometric complexity. CARSANN first estimates intrinsic dimensionality using TwoNN and constructs an intrinsic representation through principal component analysis. Local mean curvature is then estimated using a shape-operator-based formulation and control…

arXiv:2608.27574v1 Announce Type: new Abstract: Multi-label graph learning intends to capture the intrinsic complexity of real-world applications, where one sample is often related to multiple groups or consists of multiple objects. To date, a handful of multi-label graph learning methods exist, but none of them integrate training-time interpretation capability. While post-hoc graph explainers have been developed, they do not explicitly model label-dependent evidence sharing in multi-label graph learners, especially when label pairs are weakly or negatively associated. As a result, post-hoc approaches may miss how evidence should be shared or separated across different labels. This paper advances a new end-to-end self-explainable multi-label graph neural network (SEMGNN), which aims to si…

arXiv:2608.27521v1 Announce Type: new Abstract: Many dynamical processes unfold on the sphere but the default scientific machine learning architectures are Euclidean. Applying these architectures on a regular lat-lon grid causes problems: Cartesian convolutions become distorted at high latitude; 2D FFTs in Fourier neural operators incorrectly assume double periodicity; Cartesian positional encodings in ViTs distort spherical geodesic distances. Recent work moves towards natively spherical primitives, including spherical convolutions (e.g., DeepSphere or DISCO), Spherical Fourier Neural Operators (SFNOs), and geodesic attention. Here we propose Dandelion, a spherical version of Flower, a warp-based neural PDE solver. Layers of Dandelion predict a tangent-plane displacement and transport fe…

arXiv:2608.27518v1 Announce Type: new Abstract: Continual learning (CL) and model merging (MM) both aim to obtain a single model that performs well across multiple tasks, challenged respectively by catastrophic forgetting and weight-disentanglement error. In the literature, these difficulties are merely treated separately and mitigated through a variety of solutions, while the geometry induced by the base optimizer is treated as an implementation detail. In this work, we show that the two difficulties are in fact two instances of the same phenomenon: a parameter update useful for one task shifts the model's outputs on another. We formalize this shared phenomenon as \textit{task interference} and reduce it to a common layer-wise Frobenius inner product $\langle \Delta W_\ell, J_\ell(x)\ran…

arXiv:2608.27515v1 Announce Type: new Abstract: The recently introduced block-sparse featurizer (BSF; Fel et al., 2026) is similar to a sparse autoencoder (SAE), but its atomic unit is a small subspace (a block of directions) rather than a single direction. It is designed for features that live on low-dimensional manifolds, which are especially frequent in vision. This work studies the BSF's strengths and weaknesses, finding how it still somewhat suffers from classic SAE failure modes, like feature splitting and composition. We propose several architectural changes to the BSF, including a Tournament Top-K selection rule that significantly reduces feature splitting, and we also extend the block paradigm to the crosscoder.

arXiv:2608.27513v1 Announce Type: new Abstract: Softmax attention stores key and value vectors for every preceding token, causing inference memory to grow with sequence length. Recent language models incorporating Gated DeltaNet (GDN) or Kimi Delta Attention (KDA) reduce this cost by replacing the KV cache in most layers with fixed-size recurrent states. However, these recurrent states are commonly stored in FP32 and consume substantial GPU memory; their updates are memory-bandwidth bound and contribute significantly to decoding latency. To our knowledge, we are the first to study post-training quantization of recurrent states in GDN and KDA based language models. We find that uniform quantization provides a poor accuracy--storage trade-off: INT8 and FP8 already degrade accuracy on comple…

arXiv:2608.27512v1 Announce Type: new Abstract: Post-training quantization is often treated as a semantically neutral optimization for edge deployment of Large Language Models. When a full-precision source checkpoint is evaluated and quantization is applied downstream without equivalent re-evaluation, this workflow creates a structural validation--deployment gap: because quantization is a many-to-one mapping over parameter space, source-precision certification does not guarantee behavioral equivalence in the deployed configuration. We formalize this gap through Quantization Behavioral Equivalence Classes (QBECs) and prove that QBEC membership does not imply behavioral equivalence, providing a theoretical basis for quantization-triggered backdoor attacks. Building on a three-stage adversar…

arXiv:2608.27507v1 Announce Type: new Abstract: Policy Gradient for Parallel State Entropy maximization (PGPSE) expands state-space coverage by training independently parameterized policies in replicated copies of the same environment. However, its pooled team-entropy score measures only collective exploration and cannot identify policies that contribute non-redundant coverage. We introduce Marginal Coverage Credit for PGPSE (MCC-PGPSE), which combines leave-one-policy-out coverage with state-owner specialization to estimate policy-specific credit. MCC-PGPSE preserves PGPSE's pooled objective and redistributes non-negative auxiliary intrinsic rewards according to these credits without changing their total mass. This redistribution is designed to discourage redundant visitation and promote…

With millions of users across the world, Julia has been used to conduct cutting-edge research and to design new drugs, jet engines, heat pumps, and more.

Hyperprobe lets your AI agents debug production without redeploying, making it easier to find and fix issues quickly.

Today we released by far the largest update in the history of OpenClaw. It was built by 933 contributors, including 569 first-time contributors, and is composed of over 16,000 pull requests. You can read the full releas…

Most popularPro Plan $9/ month For builders ready to scale across sites. 15-day money back guarantee Up to 10k monthly events 30 websites & team members 5 years data retention Grow Action Agent & 24/7 Monitoring AI SEO…

The Cutting Room Floor (TCRF) is a much-beloved wiki dedicated to archiving and protecting unused content and unreleased builds from video games, and it’s been supported by hundreds of volunteers since its inception in…

Notifications You must be signed in to change notification settings Fork 0 Star 1 BranchesTags Open more actions menu Latest commit History 7 Commits 7 Commits Folders and files NameName Last commit message Last commit…

Notifications You must be signed in to change notification settings Fork 0 Star 0 BranchesTags Open more actions menu Latest commit History 5 Commits 5 Commits Folders and files NameName Last commit message Last commit…

Revisited: Guardian journalist Michael Safi looks into the world of artificial intelligence, exploring the dangers and promises it holds for society Today in Focus is on a summer break and will be back with new episodes from 1 September. In the meantime, we are bringing you season one of Black Box, before the launch of season two in early September. This episode was first broadcast on 21 March 2024. For decades, Eliezer Yudkowsky has been trying to warn the world about the dangers of AI. Now people are finally listening to him, but is it too late? Continue reading...

Notifications You must be signed in to change notification settings Fork 4 Star 30 BranchesTags Open more actions menu Latest commit History 438 Commits 438 Commits Folders and files NameName Last commit message Last co…

Cursor began rolling out Origin, its own code hosting platform, to paid users on Monday morning. Roughly three and a half hours later, GitHub's status page lit up with what became a six-hour-and-forty-two-minute global…

[Submitted on 26 Aug 2026] Title:Redwood: A Frontier AI Accelerator Designed, Verified, and Deployed from Scratch in 2 Weeks by AI View a PDF of the paper titled Redwood: A Frontier AI Accelerator Designed, Verified…

From the Hugging Face Incident to Twilight Factories

Advertisement • Go ad free · Aug 25, 2026 at 2:35 PM An Israel-funded think tank is churning out AI written essays to catch the attention of AI chatbots and warp search results. Photo by Christian Lue / Unsplash A…

Ollama's Pro, Max, and Team plans now use industry-standard per-token pricing with usage included on every plan.

OpenAI announced ChatGPT Work on July 9th, and have been furiously iterating on it ever since. It is an extraordinarily confusing and very powerful product. Here's what I've figured out about it so far. ChatGPT Work is actually two products The more interesting version of ChatGPT Work is the one that runs in the cloud. This can be accessed via chatgpt.com or through the ChatGPT mobile apps. Let's call it Work Cloud. If you install the ChatGPT desktop app - the app that used to be called Codex - you gain access to a thing called ChatGPT Work that can access files and run programs directly on your computer. Let's call that one Work Local. This one feels more like regular Codex re-skinned to be less intimidating to non-software-developers. For the rest of this article I'm going to talk exclu…

Dominika Wilczok Aug 24, 2026 The company is called Outer Biosciences—or Outer Bio—and its core platform, Yuna, turns surgically discarded human skin into a long-duration experimental system. Outer then combines the res…

The model under your feet changes with every OS update. Apple and Google swap the AI models inside your phone silently — no changelog, no version pin. underfoot freezes one prompt suite, captures every OS build's answer…

1/8 Which AI wrote this? “A faster model can still make an agent slower because token speed is not the load-bearing metric; completed loops are. Miss one constraint and the agent fans out into retries, stale context, an…

Notifications You must be signed in to change notification settings Fork 0 Star 0 BranchesTags Open more actions menu Latest commit History 1 Commit 1 Commit Folders and files NameName Last commit message Last commit da…

Every step in the evolution of data stacks expanded the blast radius of a data scientist. Here’s what I’ve seen so far, and here’s where we’re going in the post-AI era. Overview The pre-modern data stack (~2013) limited…