Knowledge catalogue
Follow-up to last month's post. One of the main issues people ran into was roughness or break-up on some cloned voices. 2610 is an interim update focused mostly on improving that. Reduced roughness an
I use ChatGPT a lot. Probably a lot more than is reasonable. I read David Robinson’s Atlantic piece today about leaving OpenAI and his criticism of its culture of trial-and-error / “iterative deployme
Hi folks, it's Lewis here from the post-training team at Hugging Face. We've been exploring how to train open models in different coding harnesses and wrote up a looong guide on how we solved this usi
We built an engine, Kyojin, on top of ExLlamaV3 for Strix Halo (gfx1151, ROCm), and packed two 300B-class MoE models so each fits one 128 GB machine. First release, all measured on Ryzen AI Max+ 395.
AI researchers Zainhas and Parthsareen from Ollama delivered a breakout presentation on October 2, 2026, focusing on evaluating open-source models under real‑world production traffic rather than just
arXiv:2610.00069v1 Announce Type: cross Abstract: Long-horizon ego/exo data contains rich procedural evidence, but are redundant, noisy, and costly to process or retain. We propose a compact framework
arXiv:2610.00535v1 Announce Type: cross Abstract: Uncertainty quantification is critical in scientific machine learning, where black-box, image-based models are increasingly deployed in high-stakes se
arXiv:2610.00296v1 Announce Type: cross Abstract: Token-level certainty is widely used as a proxy for correctness in LLM training and inference. However, the performance of certainty-based methods dep
Clef Decision Models are now on @ollama introducing 𝚌𝚕𝚎𝚏: our first models trained by @cloudflare's workers ai team. today, we're releasing two fast and accurate decision models that top the benchmark
arXiv:2610.01773v1 Announce Type: cross Abstract: The central challenge in de novo protein design is generating plausible, mutually compatible structures and sequences, such that each designed sequenc
arXiv:2610.01754v1 Announce Type: cross Abstract: Video Anomaly Detection (VAD) aims to temporally localize abnormal events in videos. Most existing approaches rely on dataset-specific training and cu
arXiv:2610.00237v1 Announce Type: cross Abstract: Spacecraft thermal design requires repeated evaluation of how variations in the number and spatial arrangement of heat-generating components and in th
arXiv:2610.01963v1 Announce Type: new Abstract: Emergency department (ED) triage is a high-stakes prioritization task in which demographic, socioeconomic, and system-context information may improperly
Crusoe AI Talks returns to SF. Wed Oct. 7: Join @ollama's @jmorgan and @TrajectoryLabs' @MichaelElabd for a candid conversation with Crusoe's Erwan Menard on how the calculus is shifting as closed and
arXiv:2610.01361v1 Announce Type: cross Abstract: Multilayer networks allow the modeling of interactions between the same entities across different contexts, such as temporal observations, varying set
arXiv:2610.00861v1 Announce Type: cross Abstract: Adversarial optimization under a shared ell_1 budget requires deciding not only how much perturbation to use, but also where that limited budget shoul
arXiv:2610.02175v1 Announce Type: new Abstract: Protein function annotation needs to know which predictions to distrust, not only what a model predicts. We ask whether tissue-specific interaction stru
arXiv:2610.00791v1 Announce Type: new Abstract: Enterprise information is represented through artifacts shaped by applications, projects, technologies, organizational boundaries, and local requirement
arXiv:2610.01195v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate in private environments and accumulate valuable experience from task execution, tool use, feedbac
arXiv:2610.01515v1 Announce Type: cross Abstract: Adaptive preconditioners accelerate model training, but heterogeneous client geometries can bias federated updates even when gradients are evaluated a
arXiv:2610.01638v1 Announce Type: new Abstract: Federated learning (FL) on heterogeneous edge devices must jointly accommodate unequal resource budgets and domain-shifted local data. Existing resource
arXiv:2610.01939v1 Announce Type: new Abstract: Vision language model (VLM) agents can control robots through visual feedback and action primitives, but repeated model invocations and redundant observ
arXiv:2610.01820v1 Announce Type: cross Abstract: When the system model is not fully known, measurement error and limited excitation can leave several models consistent with the same finite data. A co
arXiv:2506.11030v2 Announce Type: replace-cross Abstract: Training neural networks has traditionally relied on backpropagation (BP), a gradient-based algorithm that, despite its widespread success, su
arXiv:2610.02150v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on persistent external sources to solve sequences of knowledge-intensive tasks. Existing methods i
arXiv:2610.00580v1 Announce Type: new Abstract: In collaborative foundation model fine-tuning, client data is rarely homogeneous. Instead, clients typically possess unknown mixtures of distinct data d
arXiv:2610.02180v1 Announce Type: cross Abstract: Current controllable video generation systems often rely on 2D motion trajectories or sparse drag signals for object motion. These controls are ambigu
arXiv:2610.02189v1 Announce Type: new Abstract: Intrinsically disordered protein regions (IDRs) play central roles in cellular processes such as transcriptional regulation, signal transduction, and su
arXiv:2610.00848v1 Announce Type: cross Abstract: Vision-language models (VLMs) have emerged as powerful candidates for universal vision backbones, with representative architectures including autoregr
arXiv:2610.01076v1 Announce Type: new Abstract: Structured electronic health records (EHRs) contain a patient's clinical trajectory as a sequence of clinical codes. Answering clinical questions from s
arXiv:2610.00355v1 Announce Type: new Abstract: Efficient indoor LiDAR perception is challenging because mobile robots must understand cluttered three-dimensional environments under strict latency and
arXiv:2610.01288v1 Announce Type: new Abstract: Dynamic Movement Primitives (DMPs) provide a compact and stable formulation for trajectory representation and generalization in robot skill learning. Ho
arXiv:2610.01201v1 Announce Type: new Abstract: Object permanence, keeping track of an object's identity and position while it is occluded, is central to video representations that track, predict and
arXiv:2610.00864v1 Announce Type: cross Abstract: In this paper, we study how to achieve one-step action generation in Robotic Foundation Models (RFMs), aiming to overcome the high inference latency o
arXiv:2610.01668v1 Announce Type: new Abstract: Bio-inspired tendon-driven rigid-soft coupled dexterous fingers exhibit strong nonlinearity and configuration-dependent sensitivity, making accurate mod
arXiv:2610.00422v1 Announce Type: cross Abstract: Neural combinatorial optimization typically assumes a centralized solver that reads the whole instance. We study the opposite: combinatorial optimizat
arXiv:2410.23660v2 Announce Type: replace Abstract: Federated learning (FL) is a learning paradigm that enables collaborative training of models using decentralized data. Recently, the utilization of
arXiv:2610.02126v1 Announce Type: cross Abstract: We explore catastrophic forgetting in the context of large pre-trained models. By considering forgetting as a geometric problem in the input space of
arXiv:2610.01409v1 Announce Type: new Abstract: Reliable uncertainty estimation is essential for deploying object detectors when distribution/covariate shift and adversarial attacks may occur. Existin
arXiv:2610.01569v1 Announce Type: cross Abstract: Unmanned aerial vehicle (UAV) swarms increasingly rely on language-model agents to provide adaptive mission-level reasoning in uncertain environments.
arXiv:2601.09879v2 Announce Type: replace-cross Abstract: Recent progress in medical vision-language models (VLMs) has achieved strong performance on image-level text-centric tasks such as report gene
arXiv:2610.00538v1 Announce Type: cross Abstract: A real-time auditory scene analyzer (ASA) aims to carry out the tasks of locating, separating and classifying the sound sources present in a given aco
arXiv:2610.01098v1 Announce Type: new Abstract: Illusory matches between distinct yet visually similar 3D surfaces--doppelgangers--remain a fundamental obstacle for large-scale, in-the-wild 3D reconst
I wanted my agent to do boring web chores: check an order, star a repo, fill in a form. Every time, it hit a login page and stopped dead. My options were to give it my password and cookies, or sit the
https://www.percepta.ai/blog/can-llms-grow-their-own-capabilities https://www.percepta.ai/blog/spotlight-memory 'Our new architecture, Spotlight, replaces attention with a memory that escapes this tra
Michael Kan / PCMag: Nvidia announces a version of DGX Spark with 64 GB of unified memory for 4,999, or 1,000 more than the 128 GB version at launch — The ongoing memory shortage has prompted Nvidia t
Local AI is becoming more useful by the token. As AI agents move from experiments into everyday development, increasingly capable open models are shrinking to fit on more devices, giving builders more
I am trying to import two large datasets to enable statistical analysis. After importing the second dataset, Ollama tells me it has no record of that dataset. Intel i9-11900KF Nvidia 3080Ti 12GB Ubunt
arXiv:2610.02207v1 Announce Type: cross Abstract: 3D Gaussian avatars support fast rendering, however, their real-time animation is often challenged by the costly neural inference. We address this bot
arXiv:2610.01762v1 Announce Type: new Abstract: Streaming video LLMs must retain evidence before its relevance to future tasks is known and respond when sufficient evidence becomes available. The chal
arXiv:2610.01765v1 Announce Type: new Abstract: Spatiotemporal forecasting on hydrologic graphs is especially prone to instability in open-boundary systems, where the forecast domain exchanges fluxes
arXiv:2610.01072v1 Announce Type: new Abstract: Robotic manipulation of labware is difficult when transparent or reflective objects must be identified and localized. Coded planar fiducials are a pract
arXiv:2610.01184v1 Announce Type: cross Abstract: Remote multimodal models offer strong numerical reasoning capabilities over charts and speech, but sending private inputs risks exposing sensitive con
arXiv:2610.00979v1 Announce Type: new Abstract: Training a single LLM agent jointly across diverse interactive environments has attracted increasing attention as a route to generalist agents. Existing
arXiv:2610.02128v1 Announce Type: cross Abstract: Many applications in statistics, economics, and physics require sampling from high-dimensional categorical distributions with local dependence structu
arXiv:2610.02201v1 Announce Type: cross Abstract: High-resolution 3D generation increasingly relies on voxel latents and multi-stage pipelines that first predict active structure and then synthesize l
arXiv:2610.01408v1 Announce Type: new Abstract: Trajectory crossing remains a critical bottleneck in Flow Matching (FM), and previous works typically view these crossings from a theoretical optimizati
arXiv:2610.02023v1 Announce Type: new Abstract: While Large Language Models (LLMs) advance 3D indoor scene synthesis, current pipelines fail to retain user-specific preferences across sessions, making
arXiv:2607.09086v2 Announce Type: replace Abstract: We present Subtoken Vision Transformer (SubViT), a selective image tokenization method for fine-grained visual recognition. Standard Vision Transfor
arXiv:2610.01388v1 Announce Type: cross Abstract: We present a method for learning binaural sound localization using egomotion as a supervisory signal. Over the course of a video, the cameras directio