Knowledge catalogue
Nemotron 3.5 Lightning is available on Together AI through Dedicated Model Inference, giving teams reserved capacity and predictable performance for high-volume agent workloads. Start building: https:
NVIDIA’s Nemotron 3.5 Lightning—a fast open AI model designed for always‑on agents that perform high‑volume, specialized work—has been launched on the Together AI platform as of 11 August 2026. NVIDIA
arXiv:2512.22966v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated promise in medical knowledge assessments, yet their practical utility in real-world clinical decision
Stealing Reasoning Traces from Proprietary LLM APIs A vanity domain name (stolen-thoughts.com) for a neat paper: Anthropic, OpenAI, and Google return encrypted chain-of-thought blocks to clients that
arXiv:2608.08477v1 Announce Type: new Abstract: We present VectraYX-Vision-1B, a sub-2B vision-language model (VLM) for Spanish/LATAM cybersecurity imagery, coupling a frozen SigLIP-so400m encoder to
arXiv:2608.06691v1 Announce Type: new Abstract: Real-time human action recognition on Internet-of-Things (IoT) edge devices requires models that capture rich spatio-temporal cues within strict latency
arXiv:2608.06688v1 Announce Type: new Abstract: Vision-language-action (VLA) models provide strong semantic priors for robot navigation, but they often ignore embodiment-specific mobility constraints.
arXiv:2511.18112v3 Announce Type: replace Abstract: Recent progress in Vision-Language-Action (VLA) models has enabled embodied agents to interpret multimodal instructions and perform complex tasks. H
arXiv:2608.06445v1 Announce Type: cross Abstract: Capturing the strategic decision-making inherent in competitive human driving is critical for autonomous vehicle safety and traffic simulation. This s
Meta returns to open weights: Muse Glimmer, its first open-weights release since Llama 4, scores 35 on the Artificial Analysis Intelligence Index. It is a 30B-parameter model, and the first from Meta
Ollama allons you to import model but have you ever tried doing so ? Like running model imported from hugging face or you own model ? Any use case you wanna share ? Very curious about that submitted b
TL;DR: I am building a Windows-first local AI setup for people who want to try local LLMs without spending days choosing models, setting up Ollama, Docker, WSL, Open WebUI, agents, and tool permission
arXiv:2608.05475v1 Announce Type: new Abstract: Task knowledge is commonly stored either as text in the prompt or as an update to model weights. Text is modular but must be interpreted on every use, w
arXiv:2608.06253v1 Announce Type: new Abstract: Metabolomics knowledge is distributed across heterogeneous resources and remains difficult to translate into predictive representations. We developed Me
arXiv:2512.14751v3 Announce Type: replace-cross Abstract: Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications. However, its secur
arXiv:2608.05156v1 Announce Type: new Abstract: Post-training of large language models optimizes only parameters, while inference-time procedural scaffolds are typically designed independently of para
turns out you can get indirect prompt injection to ~0 on unseen attacks if you stack enough layers (model training + input probes + a classifier checking intent). didn't expect that a year ago. auto m
Tobias Mann / The Register: AMD acquires Toronto-based Taalas, which integrates model weights directly into silicon to boost inference performance, for an undisclosed sum — Early tech demos show model
One of the things the pelican benchmark is still useful for is visually representing (to a tiny extent) the improvements in a single model family Here's Meta AI's Spark (8th April), Spark 1.1 (9th Jul
arXiv:2608.04239v1 Announce Type: new Abstract: Spectral submanifold (SSM) reduction has emerged as a mathematically principled route to reliable nonlinear reduced-order models, capturing dynamics bey
GGUFs here: https://huggingface.co/ReadyArt/gemma-4-31B-it-scotoma-2-GGUF Disclaimer: By slop, we are specifically talking about specific tics with the model(sentence structures), but this doesn't inc
arXiv:2608.03051v1 Announce Type: new Abstract: Model Predictive Control (MPC) delivers constraint-aware control, but its reliance on online optimization limits its use on systems with fast dynamics,
arXiv:2607.15065v2 Announce Type: replace-cross Abstract: Predictive world models enable robots to plan by imagining the outcomes of their actions, but their value for control hinges on generating man
arXiv:2608.02820v1 Announce Type: cross Abstract: Chain-of-thought (CoT) monitoring is an increasingly important component of AI safety stacks but relies on the assumption that a model's reasoning tra
Introducing Muse Code and Muse Spark 1.2 Yet more evidence that the most important characteristic of any model these days is long-sequence agentic tool calling. Meta shipped their own coding agent as
arXiv:2608.03690v1 Announce Type: new Abstract: Point-of-care cardiac devices such as smartwatches and handheld ECG recorders typically capture 1--2 leads, yet existing ECG foundation models are archi
arXiv:2608.03428v1 Announce Type: cross Abstract: Image based dietary assessment offers a scalable alternative to self reported food diaries, yet fine-grained food recognition remains challenging due
arXiv:2608.02032v1 Announce Type: new Abstract: Modern language models are built primarily from Transformers, recurrent models, and their hybrid architectures. Transformers rely on token-level attenti
arXiv:2608.00146v1 Announce Type: new Abstract: We introduce DiffusionGemma, an experimental open-weight language model that uses discrete diffusion to generate text at exceptionally high speed. Rathe
arXiv:2407.15260v3 Announce Type: replace Abstract: Statistical Shape Models (SSMs) excel at identifying population level anatomical variations, which is at the core of various clinical and biomedical
arXiv:2608.01034v1 Announce Type: new Abstract: We introduce Opt.Gear, a foundation model designed for efficient on-device deployment, real-tim inference, and strong task capability. It includes a den
arXiv:2607.29491v1 Announce Type: cross Abstract: Reinforcement-learning-based quantum architecture search (RL-QAS) repeatedly optimizes a variational quantum eigensolver (VQE) after extending a circu
📢Meet Qwen3.8-Max — our most capable model to date. Next week, the open weights of Qwen3.8-Max will be released, and Qwen3.8-27B is also going open-weights to meet you all!🎉 Qwen3.8-Max, a new bar for
arXiv:2607.28802v1 Announce Type: new Abstract: Existing evaluations often reduce agent failures to system-level outcomes, obscuring where the fault originated and which intervention would improve the
arXiv:2512.12816v2 Announce Type: replace Abstract: We study how to allocate resources for training and deployment of machine learning (ML) models under concept drift and limited budgets. We consider
arXiv:2607.29181v1 Announce Type: cross Abstract: Agentic assistants capable of proactive, personalized interactions require structured models of user intent and workflow. However, building these mode
arXiv:2607.28035v1 Announce Type: new Abstract: Irregular multivariate time series are widely encountered in applications such as healthcare monitoring, human activity recognition, and environmental s
arXiv:2607.28423v1 Announce Type: new Abstract: Radiomics and imaging foundation models promise non-invasive biomarkers of tumour biology, yet predictive signatures may reflect tumour volume or acquis
arXiv:2607.27303v1 Announce Type: cross Abstract: Temporal heterogeneous graphs offer a natural abstraction for dynamic relational systems in which diverse node and relation types co-exist and evolve
arXiv:2607.26063v1 Announce Type: cross Abstract: Personalised learning systems often assume that mathematical ability is combined of discrete abilities, acquired sequentially and dependent upon first
arXiv:2607.26981v1 Announce Type: new Abstract: Large language models are increasingly used as decision aids whose probability judgments shape downstream choices. Whether those judgments carry a syste
We are committed to pushing the model frontier across cost efficiency, capability, and speed. Starting today, we are reducing prices for GPT-5.6 Luna by 80% and GPT-5.6 Terra by 20% , and offering a f
arXiv:2607.25487v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models translate natural-language commands into robot action sequences, but leading systems on the LIBERO-Plus robustness b
Figure 1: CUDA-to-MLX optimization translation map. CUDA optimization knowledge can be translated into architecture-native MLX strategies rather than copied instruction-for-instruction. We face a new
arXiv:2607.25583v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) and low-bit quantization are now standard tools for adapting language models under tight compute budgets, yet the
arXiv:2607.24904v1 Announce Type: cross Abstract: Standard vision-language models (VLMs) suffer from Moravec's paradox: they excel at complex offline visual reasoning but struggle with simple streamin
arXiv:2607.25357v1 Announce Type: cross Abstract: Long-context recall in linear-time sequence models highlights a tradeoff in how they write to memory. State-based linear models, such as state-space m
arXiv:2605.05540v2 Announce Type: replace Abstract: Fast surrogate modeling for high-dimensional physical dynamics requires more than low short-term error: useful models must roll out efficiently whil
arXiv:2107.08183v2 Announce Type: replace Abstract: High-dimensional state and action spaces combined with sparse reward structures in reinforcement learning (RL) environments typically require advanc
arXiv:2210.05487v3 Announce Type: replace Abstract: Unlike most neural language models, humans learn language in a rich, multi-sensory and, often, multi-lingual environment. Current language models ty
arXiv:2607.24029v1 Announce Type: new Abstract: Precise control of soft manipulators remains challenging due to the difficulty of developing accurate yet computationally tractable models for model-bas
arXiv:2607.23517v1 Announce Type: new Abstract: We present a real-time human-centric world model for upper-body interactive generation, aiming to synthesize coherent local world dynamics centered on a
arXiv:2607.23123v1 Announce Type: new Abstract: Existing evaluations of large language models cover knowledge, reasoning, coding, and tool use, but they rarely treat a verifiable deliverable produced
Michael Nuñez / VentureBeat: The Agentic AI Foundation updates MCP with a fully stateless architecture, a hardened authentication model, a formal 12-month deprecation policy, and more — The Model Cont
The Kimi K3 architecture figure for yesterday's big open-weight model release, along with some observations and thoughts. 1. Yes, it looks relatively complicated, but it's essentially a scaled-up prod
server + ui: fix stream routes for model names containing a slash (#26137) server + ui: refactor resumable stream routes to query string conv_id The conversation id can embed a model name containing s
arXiv:2607.22516v1 Announce Type: cross Abstract: A central design principle in modern machine learning and artificial intelligence is to align a model's inductive bias with the structure of its input
arXiv:2512.04223v2 Announce Type: replace Abstract: Modelling the complexity and diversity of human activity scheduling behaviour is inherently challenging. We demonstrate ActVAE, a deep conditional-g
This post covers Opus 5’s improvements and practical guidance for AI engineers integrating the model into agentic systems and production inference workloads on Amazon Bedrock. See the documentation fo
I maintain Tagvico, an open-source companion for Paperless-ngx. I added Ollama because document text is exactly the kind of data many people do not want to send to a hosted model. The surprising failu