Knowledge catalogue
There is a lot of buzz around running 100B parameter models on cheap local hardware using ternary (1.58-bit) quantization like Microsoft's BitNet architecture. The theoretical hardware shortcuts are i
I apologize that this question has been asked in various flavors over time, but I couldn't find anything in the posts before that matches the options I have. I have a PC and a mac, both available in m
Hello, I've been learning how to use local LLMs for a year or so on my workstation, using a RTX3090. Current setup : - i5 12400 - 64gb RAM - RTX 3090 - OS : Fedora KDE workstation I'm using LMStudio t
RTX 4070, 32gb system ram, Linux. NVIDIA-SMI 610.43.03, KMD Version: 610.43.03, CUDA UMD Version: 13.3 Systemd service modifications: [Service] Environment='OLLAMA_HOST=0.0.0.0:11434' Environment='OLL
A new model launch is not a product update ‼ It's one of three things, and you don't know which until you test it. Sometimes it's nothing: the model improved inside the same distribution, your harness
arXiv:2607.09424v3 Announce Type: replace-cross Abstract: We present Soofi S 30B-A3B, a sovereign, open-source Mixture-of-Experts (MoE) hybrid Mamba Transformer foundation model for German and English
arXiv:2607.20441v1 Announce Type: new Abstract: Every information ecosystem produces beliefs that shape strategic decisions. Both human analysts and AI systems inherit the blind spots of their informa
I’m not affiliated with this project, but I’ve been running it recently and I’m surprised it hasn’t received more attention here: https://github.com/fewtarius/CachyLLama CachyLLama is a fork of llama.
arXiv:2607.20458v1 Announce Type: cross Abstract: Large language model (LLM) agents operating over extended dialogues accumulate vast amounts of information, yet existing memory systems either retain
arXiv:2607.20467v1 Announce Type: new Abstract: While parallel decoding is central to the efficiency of Diffusion Large Language Models (dLLMs), current strategies are often hindered by overly conserv
I launched a new session and tasked GLM to create an implementation plan for a spec. The plan was on the bigger side, about 5k lines. I started with 0% 5h used and ended with 80% used. A few more twea
arXiv:2508.16947v2 Announce Type: replace-cross Abstract: Despite significant progress, imitation learning-based autonomous driving planners remain largely restricted to reproducing high-frequency bia
So I've taken some time to actually test laguna on a few of my own projects. I wanted to share as I feel most peoples comments at this point have just been about getting it running or saying it doesnt
arXiv:2607.20723v1 Announce Type: cross Abstract: This work presents LeakyLMs, a set of attacks that leak proprietary model, architecture, and deployment information from production language models. L
arXiv:2607.20709v1 Announce Type: new Abstract: Traditional agent development is split across prompt templates, tool schemas, callback code, and workflow graphs. We present NVIDIA Object-Oriented Agen
arXiv:2510.16703v3 Announce Type: replace-cross Abstract: The classical notion of causal effect identifiability is defined in terms of treatment and outcome variables. In this paper, we consider the i
arXiv:2607.21419v1 Announce Type: new Abstract: In long-horizon LLM agent reinforcement learning, weak policies often repeat similar failures, producing uninformative rollout trajectories and limiting
arXiv:2607.21447v1 Announce Type: cross Abstract: The ability to handle long-term memory in LLMs is becoming increasingly critical, yet existing benchmarks remain English-centric and rely on aggregate
arXiv:2607.20767v1 Announce Type: new Abstract: We introduce Rushes, a dataset and benchmark for studying revealed human engagement preferences in interactive narrative environments. Rushes is collect
arXiv:2603.06642v2 Announce Type: replace-cross Abstract: Test-Time Training (TTT) language models replace the KV-cache with fast weights updated during inference, achieving O(1) memory but suffering
arXiv:2607.21325v1 Announce Type: cross Abstract: Autonomous AI agents increasingly execute actions, invoke tools, and operate on protected resources with limited human oversight. Existing authenticat
arXiv:2603.04910v2 Announce Type: replace-cross Abstract: Imitation learning from human demonstrations has achieved significant success in robotic control, yet most visuomotor policies still condition
arXiv:2607.20638v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated strong capabilities in code generation and reasoning, yet their ability to perform temporal reasoning ove
Been wanting to build this for a while, finally sat down and did it. It's a Flask app where you upload a PDF, it chunks and embeds it, and then you can ask questions and get answers pulled only from t
arXiv:2607.19476v1 Announce Type: new Abstract: Detectors for AI-generated video are evaluated offline. A clip is decoded to pixels and scored once, increasingly by a large vision-language model. Dete
arXiv:2607.19787v1 Announce Type: cross Abstract: Polarimetric synthetic aperture radar (PolSAR) image classification is a representative task for physics-aware GeoAI, where land-cover semantics are c
arXiv:2607.20002v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) have emerged as general-purpose models for time series analysis, but pretraining alone is often insufficient for
arXiv:2607.19701v1 Announce Type: new Abstract: VLMs are increasingly deployed in AD systems, creating an urgent need for rigorous safety evaluation under rare yet safety-critical scenarios. Among the
Welcome to The Blueprint, a new feature where we highlight how Google Cloud customers are tackling unique and common challenges across industries using the latest AI and cloud technologies. We hope to
We're parsing some of the hardest financial documents into clean, plaintext/structured outputs through a live webinar. Come check it out! https://watch.getcontrast.io/register/llamaindex-from-complex-
Vibe coding isn't just for your PC anymore. Here's LLM Hub generating and previewing code entirely on an iPhone. Everything runs locally. Using the RunAnywhere SDK, Timmy Qian ported LLM Hub, an Andro
Interesting finding on frontier models. It turns out that frontier models can write proofs but stumble on faithfully copying a long block of text. This has huge implications. It sounds trivial, which
arXiv:2607.13110v1 Announce Type: cross Abstract: Since the paradigm centered on convolutional neural networks and recurrent architectures was established in 2020, the fundamental backbone networks fo
arXiv:2607.13298v1 Announce Type: new Abstract: In online streaming video understanding, a video stream continues to arrive and queries may be issued at any time. Because streaming frames grow without
arXiv:2607.13115v1 Announce Type: new Abstract: Small language models (SLMs) have shown promise for zero-shot molecular property prediction from SMILES strings, yet they often suffer from structural b
arXiv:2607.13172v1 Announce Type: new Abstract: We address the problem of safely training an agent policy and deploying a good and safe policy, in settings where the environment dynamics are unknown a
arXiv:2607.13189v1 Announce Type: cross Abstract: We present RAGthoven, our system for SemEval-2026 Task 1 (MWAHAHA), Subtask A (multilingual constrained humor generation in English, Spanish, and Chin
arXiv:2607.13124v1 Announce Type: cross Abstract: Structured pruning is a hardware-friendly way to compress LLMs, but it is mostly validated on multiple-choice recognition tasks, while the same compre
arXiv:2607.10350v1 Announce Type: cross Abstract: Recent VLM and VLA systems have improved robotic perception and action prediction, yet long-horizon embodied agents still require a general runtime la
arXiv:2607.10183v2 Announce Type: replace-cross Abstract: Running large language models on consumer devices such as laptops and desktops is challenging because model weights often exceed GPU memory ca
arXiv:2607.11949v1 Announce Type: cross Abstract: We present a clinically deployed end-to-end auto-contouring system for cervical cancer radiotherapy planning, anchored by the Boundary-Aware Transform
Blog and paper: https://research.nvidia.com/labs/gear/robottt/ Presented to you from NVIDIA GEAR Lab. Please check out Yunfan's technical deep dive! https://x.com/YunfanJiang/status/207740099214934055
arXiv:2607.11959v1 Announce Type: new Abstract: Greenhouse reinforcement learning can test climate-control ideas at a speed and scale that is difficult to achieve with crop experiments alone. For smar
arXiv:2607.11020v2 Announce Type: replace Abstract: Continual learning promises a language model that keeps acquiring knowledge after training, with each new fact written into its weights. Whether wei
arXiv:2601.08010v3 Announce Type: replace Abstract: Vision-language models achieve strong performance across a wide range of multimodal understanding and reasoning tasks, yet their multi-step reasonin
arXiv:2602.05513v3 Announce Type: replace-cross Abstract: Bimanual dexterous manipulation relies on integrating multimodal inputs to perform complex real-world tasks. To address the challenges of effe
arXiv:2607.12570v1 Announce Type: cross Abstract: Multiscale problems are notoriously difficult to tackle using traditional numerical methods, as accurately resolving fine-scale features often require
arXiv:2607.12462v1 Announce Type: new Abstract: Existing traffic forecasting models commonly focus on extracting spatial dependencies, particularly global spatial information, which characterizes the
arXiv:2607.12884v1 Announce Type: new Abstract: Patients seeking medical information often ask questions that embed incorrect assumptions or misconceptions. In such cases, safe medical communication r
Excited for our first general model Inkling -- open weights, 975B, natively multimodal (text, image, audio). Available on Tinker, HuggingFace and partners. It is yours to personalize and use openly. I
arXiv:2501.05396v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in high-stakes decisions such as hiring and college admissions, making their social bias a critic
arXiv:2505.16157v2 Announce Type: replace Abstract: Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Trans
arXiv:2607.12077v1 Announce Type: new Abstract: Multi-agent language-model systems increasingly route local interactions, yet the runtime interaction graph is often treated as an implementation detail
arXiv:2411.02989v2 Announce Type: replace Abstract: How diverse are the outputs of large language models when diversity is desired? We examine the diversity of responses of several language models to
arXiv:2607.11946v1 Announce Type: new Abstract: Language identification is an important step toward integrating endangered Australian Aboriginal languages (AALs) into speech technologies supporting la
arXiv:2607.12593v1 Announce Type: cross Abstract: The evolution of energy-efficient ultra-low-power (ULP) parallel processors and the diffusion of convolutional neural networks (CNNs) are fueling the
arXiv:2607.12627v1 Announce Type: new Abstract: We propose an architecture for learning the dynamics of mechanical systems based on discrete forced Euler-Lagrange equations on Lie groups using only po
arXiv:2607.12599v1 Announce Type: new Abstract: Time-series anomaly detection is increasingly important in IoT systems, sensor networks, and edge monitoring applications, where models must operate und
arXiv:2607.12713v1 Announce Type: cross Abstract: Generated tokens are a direct driver of the cost, latency, and energy of generative AI (GAI) code editing. We show the format of feedback is a lever o
arXiv:2607.12663v1 Announce Type: new Abstract: Accurate differentiation between gastric adenoma and carcinoma during endoscopy is critical for clinical decision-making. Yet, this task is highly chall