Knowledge catalogue
You can now run Claude Desktop fully on local models with one toggle. Open @ollama on, pick a model. Cowork and Claude Code inside the desktop app run on it. Flip it off, you're back to Anthropic. Why
Have you been hearing a lot about 'AI agents' lately but aren't sure how to actually start building them? You don't need a background in machine learning or years of software experience to get started
Your closed model refused a task it should have done. Ours didn't. DeepSeek V4 Pro on Fireworks: beats Fable 5 on SWE-Bench and LiveCodeBench, a third of the cost per solved task, and it doesn't decli
ollama ps settles this in one line, and almost nobody runs it before changing their quant. The PROCESSOR column reports exactly one of three things: 100% GPU - every layer on the GPU 100% CPU - the GP
Your organization is not spending enough of its efforts on bolstering cybersecurity during the window before open weights Mythos-class models/harnesses become available. The HuggingFace incident shows
Z.ai: Z.ai releases GLM-5.3-Flash, the first natively multimodal GLM-5 series model, with 320B parameters, saying it outperforms GLM-5.2 at “one-tenth the price” — We introduce GLM-5.3-Flash, the firs
arXiv:2608.24422v1 Announce Type: new Abstract: Recovering the full 3D spine anatomy from intraoperative ultrasound is an ill-posed inverse problem, as the complete structure must be inferred from inc
I ran 11 uncensored variants of Gemma 4 12B that I grabbed from huggingface, sorting by downloads. 10 full abliterations plus 2 LoRA adapters which were requested to be added in the comparison, agains
On August 25 2026, Mia AI Lab announced that the Qwen‑3.8 Flash model would be released in 22 hours, noting it can run locally without a sleep restriction. The tweet includes a link to the Hugging Fac
With hopes of a Qwen3.8-35B-A3B release now mostly dashed, many people including myself are looking at fine-tunes and other variants of Qwen3.6-35B-A3B to run on VRAM-limited hardware. I decided to tr
arXiv:2608.21468v1 Announce Type: new Abstract: While three-dimensional (3D) point clouds are widely used in civil engineering, mainstream LiDAR systems such as Terrestrial Laser Scanning (TLS) are ph
arXiv:2608.22910v1 Announce Type: cross Abstract: We develop a finite-width geometric framework describing how learned feature geometries are organized, transported, and selectively aligned in deep ne
arXiv:2608.23182v1 Announce Type: cross Abstract: We present a comparative study of label-free metrics for assessing the quality of representations in deep neural networks to understand their reliabil
arXiv:2608.23421v1 Announce Type: new Abstract: Natural Language Processing (NLP) has grown rapidly over the past decade, driven by digital transformation in the Arab world, social media, and large la
arXiv:2608.22672v1 Announce Type: new Abstract: Energy system operation contains a loop of work that automation has never taken over: posing the optimization problem the current cycle should solve, di
arXiv:2607.27910v2 Announce Type: replace Abstract: Inference time defences against vision language model jailbreaks often subtract a calibrated direction from the residual stream at a chosen decoder
arXiv:2608.21480v1 Announce Type: cross Abstract: A Markov chain is a widely used stochastic process modelling random events over time. These models are built on subsets of the entire dataset, referre
arXiv:1706.02795v1 Announce Type: cross Abstract: Kiva is an online non-profit crowdsouring microfinance platform that raises funds for the poor in the third world. The borrowers on Kiva are small bus
SemiAnalysis: A detailed look at Jalapeño, OpenAI's ASIC developed with Broadcom in 16 months, which beat Nvidia, AMD, and Google chips on multiple top open-weight models — OpenAI's self-designed ASIC
arXiv:2608.21779v1 Announce Type: new Abstract: Dimensionality-reduction (DR) methods are routinely judged by how well each point's k nearest neighbors survive the 2-D embedding (recall@k, trustworthi
arXiv:2603.27530v2 Announce Type: replace Abstract: Bock's 1971 algorithm is an exact primal--dual method for the minimum-cost arborescence problem, but its Algol presentation obscures the interaction
arXiv:2606.19230v2 Announce Type: replace Abstract: This work presents an extension to Pareto Front Guided Sampling (PFGS), a Human-in-the-Loop (HitL) Bayesian Optimization (BO) framework in which Gau
arXiv:2602.14255v2 Announce Type: replace Abstract: Industrial robots are increasingly deployed in construction and manufacturing tasks, where the deployment of end-to-end visuomotor policies is chall
arXiv:2506.20073v2 Announce Type: replace-cross Abstract: Spatio-temporal data mining plays a pivotal role in informed decision making across diverse domains. However, existing models are often restri
arXiv:2608.22945v1 Announce Type: new Abstract: Federated learning has traditionally been formulated as a single-objective optimization problem, primarily focused on maximizing model utility. In real-
arXiv:2608.23235v1 Announce Type: new Abstract: Event extraction aims to identify event triggers, classify event types, and extract arguments to construct structured event representations. Despite str
arXiv:2608.23276v1 Announce Type: new Abstract: Objective. To develop and evaluate a cuffless continuous blood pressure (BP) estimator using temporal physiological and demographic features. We propose
arXiv:2510.19347v2 Announce Type: replace-cross Abstract: Most machine learning models are vulnerable to adversarial examples, which poses security concerns on these models. Adversarial examples are c
arXiv:2608.22994v1 Announce Type: cross Abstract: Training large language models is costly. How low a loss the same compute can ultimately reach depends on how each step's gradient is converted into a
arXiv:2608.21818v1 Announce Type: new Abstract: Thin-walled truncated conical shells are widely used in aerospace, marine, offshore, and lightweight infrastructure systems due to their high strength-t
arXiv:2608.22235v1 Announce Type: new Abstract: Pore-scale flow governs transport and permeability behaviour in porous media engineering applications, yet repeated lattice Boltzmann method (LBM) simul
arXiv:2608.21570v1 Announce Type: new Abstract: Deploying a safety layer for large language models on commodity hardware is constrained by the guards available to do it: current open guard models hold
arXiv:2608.23261v1 Announce Type: new Abstract: Event extraction is fundamental to information extraction. Prior approaches often separate event detection and argument extraction or depend on dataset-
arXiv:2608.21893v1 Announce Type: cross Abstract: Scalable Vector Graphics are a fundamental medium for resolution-independent visual content, yet the deep learning community lacks a continuous, dense
arXiv:2608.23137v1 Announce Type: new Abstract: Existing articulatory corpora based on real-time MRI and electromagnetic articulography capture tongue shape and motion but do not provide traceable lab
arXiv:2608.21385v1 Announce Type: cross Abstract: Social media has become a central arena in which armed conflicts are contested, yet the pro-Israel and pro-Palestine communities on Telegram, whose br
arXiv:2608.22713v1 Announce Type: new Abstract: Clinical diagnosis requires progressive integration of patient history, physical examination, laboratory findings, medical images, and diagnostic-inform
arXiv:2608.21391v1 Announce Type: cross Abstract: In this research-to-practice paper we present a survey that can be used to assess students' AI knowledge. As the use of artificial intelligence (AI),
arXiv:2403.04931v4 Announce Type: replace Abstract: As the capabilities of artificial intelligence (AI) continue to expand rapidly, Human-AI (HAI) Collaboration, combining human intellect and AI syste
arXiv:2608.22496v1 Announce Type: new Abstract: Autonomous underwater vehicles (AUVs) rely on the fusion of inertial navigation systems (INS) and Doppler velocity logs (DVL) for accurate navigation. B
.. didn't llama.cpp aka ggml get acquired by Huggingface not too long ago? How would this sale affect llama.cpp and ggml? What are possible risks, and did ggerganov share his opinions or potential nex
arXiv:2608.23167v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) exhibit strong parallel decoding capabilities by denoising multiple tokens in a single generation step. However, this p
arXiv:2608.22338v1 Announce Type: new Abstract: Interactive PDF form fields are often absent from documents that visually resemble forms, leaving users unable to enter data without printing or externa
arXiv:2608.23478v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models can turn multimodal context into robot actions, but their action decoders are still trained largely by behavior cl
arXiv:2608.23503v1 Announce Type: new Abstract: Text-based person anomaly search requires distinguishing individuals based on fine-grained, context-dependent behaviors rather than mere appearance. Exi
arXiv:2608.23144v1 Announce Type: cross Abstract: Low-bit weight quantization saves storage but leaves errors that degrade language-model quality. We introduce Activation-Weighted Seeded Residual Codi
arXiv:2608.21400v1 Announce Type: new Abstract: Dense traffic is inherently interactive. The ego vehicle and surrounding agents continuously influence each other's reactions, making 'what-if' reasonin
arXiv:2608.23536v1 Announce Type: cross Abstract: The continual evolution of malware variants necessitates detection systems that can adapt to new threats without retraining from scratch. However, con
arXiv:2608.22313v1 Announce Type: new Abstract: Learning multi-label image classification with incomplete annotations is a challenging task that has been widely studied for its superior trade-off betw
arXiv:2608.23400v1 Announce Type: cross Abstract: Discrete Diffusion Models (DDMs) have recently been introduced to recommendation systems, modeling user history as a token generation process via iter
arXiv:2608.21736v1 Announce Type: new Abstract: Rare unsafe behaviors in large language models can remain practically significant even when their probability is extremely small, particularly at deploy
arXiv:2602.09555v3 Announce Type: replace Abstract: Recent advances in block diffusion language models have demonstrated competitive performance and strong scalability on reasoning tasks. However, the
arXiv:2512.17730v2 Announce Type: replace Abstract: Detectors of AI-generated images tend to inherit the biases of the data they are trained on: models fitted to GAN imagery learn to treat GAN-specifi
arXiv:2510.04617v3 Announce Type: replace Abstract: Mathematical reasoning is a primary indicator of large language models (LLMs) intelligence. However, existing LLMs exhibit failures in robustness an
arXiv:2501.16760v2 Announce Type: replace Abstract: Automated interpretation of seismic images using deep learning methods is challenging because of the limited availability of training data. Few-shot
arXiv:2608.23297v1 Announce Type: cross Abstract: Data assimilation (DA) is an essential tool for prediction and understanding in the geosciences. DA combines simulation programs representing scientif
arXiv:2608.22356v1 Announce Type: new Abstract: Explainable AI (XAI) research has produced a plethora of explanation techniques, yet user studies repeatedly show that available explanations are not ef
arXiv:2512.13095v3 Announce Type: replace Abstract: To address the limited capability expansion and low sample efficiency of Reinforcement Learning (RL), recent methods have integrated ''hints'' into
arXiv:2608.22066v1 Announce Type: cross Abstract: Attention-based multiple instance learning (ABMIL) using pathology foundation model embeddings is effective for slide-level tasks, but exhaustive infe
arXiv:2608.22644v1 Announce Type: cross Abstract: As the use of Artificial Intelligence (AI) and Large Language Models (LLMs) is becoming common in everyday applications, their ability to interpret na