Knowledge catalogue
arXiv:2511.14967v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown great promise in generating structured diagrams from natural language descriptions, particularly Merma
arXiv:2604.24625v1 Announce Type: cross Abstract: Unified multi-modal understanding/generative models have shown improved image editing performance by incorporating fine-grained understanding into the
arXiv:2604.24096v1 Announce Type: cross Abstract: Training reliable respiratory sound classification models remains challenging due to the limited size and subject diversity of datasets. Ensemble meth
arXiv:2604.23289v1 Announce Type: cross Abstract: Due to the unprecedented success of deep learning, it has become an integral component in several multimedia computing applications in todays world. U
arXiv:2604.23539v1 Announce Type: new Abstract: The rapid proliferation of Generative AI necessitates rigorous documentation standards for transparency and governance. However, manual creation of Mode
arXiv:2509.04802v3 Announce Type: replace Abstract: As large language models increasingly deployed into agentic systems, existing methods face critical gaps in observing, assessing, and mitigating dep
arXiv:2604.23108v1 Announce Type: cross Abstract: Large Language Models (LLMs) based on Mixture-of-Experts (MoE) are pivotal in industrial applications for their ability to scale performance efficient
arXiv:2506.01897v5 Announce Type: replace Abstract: With increasing size of large language models (LLMs), full-parameter fine-tuning imposes substantial memory demands. To alleviate this, we propose a
arXiv:2506.20332v4 Announce Type: replace Abstract: Vision-language model-based mobile agents have gained the ability to understand complex instructions and mobile screenshots, benefiting from reinfor
arXiv:2604.23620v1 Announce Type: new Abstract: We present Move-Then-Operate, a Vision language action framework that explicitly decouples robotic manipulation into two distinct behavioral phases: coa
arXiv:2604.23530v1 Announce Type: cross Abstract: Multi-turn, long-horizon tasks are increasingly common for large language models (LLMs), but solving them typically requires many sequential model inv
arXiv:2604.24158v1 Announce Type: new Abstract: Evaluating nuanced conversational travel recommendations is challenging when human annotations are costly and standard metrics ignore stakeholder-centri
arXiv:2604.23977v1 Announce Type: new Abstract: Accurate biomedical image classification under low-resource conditions remains challenging due to limited annotations, subtle inter-class visual differe
arXiv:2604.23789v1 Announce Type: new Abstract: While video foundation models excel at single-shot generation, real-world cinematic storytelling inherently relies on complex multi-shot sequencing. Fur
arXiv:2604.23930v1 Announce Type: cross Abstract: When, in terms of the number of data points, the size of a dataset exceeds available computing resources, or when labeling is expensive, an attractive
NVIDIA Nemotron 3 Nano Omni is a multimodal large language model that unifies video, audio, image, and text understanding for enterprise Q&A, summarization, transcription, and document intelligence, w
Nemotron 3 Nano Omni is available locally on Ollama! This requires the latest Ollama 0.22 release. Meet Nemotron 3 Nano Omni 👋 Our latest addition to the Nemotron family is the highest efficiency, ope
Nemotron 3 Nano Omni is now in LM Studio! A new 30B multi-modal MoE from @nvidia Supports Image input, reasoning, and tool use Requires ~25GB to run locally 🔥🚀 https://lmstudio.ai/models/nemotron-3-om
arXiv:2604.24696v1 Announce Type: new Abstract: Agentic artificial intelligence systems promise to accelerate scientific workflows, but neuroimaging poses unique challenges: heterogeneous modalities (
new in ml-intern: you can now actually see what's going on inside added native metric logging + trackio integration. every training run the agent kicks off now has live curves you can watch in real ti
arXiv:2604.23106v1 Announce Type: cross Abstract: Existing multi-agent Large Language Model (LLM) frameworks for code generation typically use execution feedback and improve iteratively using Input/Ou
arXiv:2603.14228v2 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) has become a cornerstone of parameter-efficient fine-tuning (PEFT). Yet, its efficacy is hampered by two fundamental limi
Mobile app security company NowSecure Inc. today announced Mobile App Risk Intelligence, new capabilities that are designed to give enterprises evidence-based visibility into third-party mobile apps a
Nvidia Corp. today launched a powerful reasoning artificial intelligence model that unifies text, vision and speech, capable of acting as the “brains” of faster, smarter agentic AI applications. Dubbe
Kyt Dotson / SiliconANGLE: Nvidia launches Nemotron 3 Nano Omni, an open multimodal model with a 30B-A3B hybrid MoE architecture; the Nemotron 3 family saw 50M+ downloads in the past year — Nvidia Cor
AI agent systems today juggle separate models for vision, speech and language — losing time and context as they pass data from one model to the other. Unveiled today, NVIDIA Nemotron 3 Nano Omni is an
@NVIDIA Nemotron 3 Nano Omni is now on Together AI. Enterprise multimodal AI — video, audio, image, documents & text — optimized for speed and scale. ✅ ~3B active params, 9x higher throughput ✅ Fully
Today, we are excited to announce the day zero availability of NVIDIA Nemotron 3 Nano Omni on Amazon SageMaker JumpStart. In this post, we walk through the model architecture and key capabilities of N
NVIDIA Nemotron 3 Nano Omni, a compact multimodal AI model, is now available for deployment on Vultr's cloud infrastructure, enabling developers to run efficient vision and language tasks at scale. Th
NVIDIA Nemotron 3 Nano Omni is a 30B hybrid mixture-of-experts model that brings multimodal perception and reasoning into a single system, natively supporting text, image, video, and audio inputs whil
arXiv:2506.05480v4 Announce Type: replace-cross Abstract: We introduce ODE-GS, a novel approach that integrates 3D Gaussian Splatting with latent neural ordinary differential equations (ODEs) to enabl
arXiv:2509.20086v2 Announce Type: replace Abstract: Phonemization is a critical component in text-to-speech synthesis. Traditional approaches rely on deterministic transformations and lexica, while ne
arXiv:2604.00270v2 Announce Type: replace Abstract: Recent large multimodal models (LMMs) have made rapid progress in visual grounding, document understanding, and diagram reasoning tasks. However, th
arXiv:2604.24762v1 Announce Type: new Abstract: Shot Boundary Detection (SBD) aims to automatically identify shot changes and divide a video into coherent shots. While SBD was widely studied in the li
arXiv:2604.23012v1 Announce Type: cross Abstract: This paper presents a complete, end-to-end on-device vision machine learning pipeline, comprising data acquisition, two-layer CNN training with Adam o
arXiv:2507.06542v4 Announce Type: replace Abstract: Decentralized learning provides a scalable alternative to parameter-server-based training, yet its performance is often hindered by limited peer-to-
arXiv:2510.01409v2 Announce Type: replace Abstract: System logs represent a valuable source of Cyber Threat Intelligence (CTI), capturing attacker behaviors, exploited vulnerabilities, and traces of m
Open Models & a potential looming Haiku-apocalypse? 🚀 chart comparison UI courtesy of @OpenRouter there's a large class of problems where you don't need frontier intelligence. you want cheap, fast, an
OpenAI announced the availability of its models, including Codex, and managed agent capabilities on Amazon Web Services (AWS) infrastructure. This integration enables AWS customers to access OpenAI's
OpenClaw 2026.4.26 🦞 🎙️ Google Live Talk 🦙 Better Ollama/local models 🧳 Bring over Claude + Hermes setups 🔐 One-command Matrix E2EE Big release. Local models eat well. https://github.com/openclaw/open
arXiv:2603.12365v2 Announce Type: replace-cross Abstract: History-dependent constitutive models serve as macroscopic closures for the aggregated effects of micromechanics. Their parameters are typical
arXiv:2604.23712v1 Announce Type: cross Abstract: Recent advances in formal theorem proving have focused on Olympiad-level mathematics, leaving undergraduate domains largely unexplored. Optimization,
arXiv:2604.22783v1 Announce Type: cross Abstract: Parameter-Efficient Fine-Tuning (PEFT) has become the standard for adapting large language models (LLMs). In this work we challenge the wide-spread as
arXiv:2509.19602v2 Announce Type: replace Abstract: Parameter-efficient fine-tuning methods have emerged as a promising solution for adapting pre-trained models to various downstream tasks. While thes
arXiv:2604.22835v1 Announce Type: cross Abstract: Autonomous parking remains a critical yet challenging task in intelligent driving systems, particularly within constrained urban environments where ma
arXiv:2511.08484v2 Announce Type: replace Abstract: We propose patching for large language models (LLMs) like software versions, a lightweight and modular approach for addressing safety vulnerabilitie
arXiv:2512.20298v2 Announce Type: replace-cross Abstract: Growing reliance on LLMs for psychiatric self-assessment raises questions about their ability to interpret qualitative patient narratives. Thi
arXiv:2410.05970v3 Announce Type: replace-cross Abstract: Multimodal document understanding is a challenging task to process and comprehend large amounts of textual and visual information. Recent adva
arXiv:2604.22934v1 Announce Type: new Abstract: LLM-based agents for text-to-SQL often struggle with latency-performance trade-off, where performance improvements come at the cost of latency or vice v
arXiv:2604.23580v1 Announce Type: cross Abstract: Physics-aware symbolic simulation of 3D scenes is critical for robotics, embodied AI, and scientific computing, requiring models to understand natural
Pi + local models are definitely really cool! Short demo to clean up my Desktop: > terminal 1: llama-server -hf unsloth/Qwen3.5-9B-GGUF:UD-Q4_K_XL > terminal 2: simply type 'pi' and start talking to i
arXiv:2604.22823v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) rely on multimodal pre-training over diverse data sources, where different datasets often induce complementar
arXiv:2505.01700v3 Announce Type: replace Abstract: Existing protein-ligand docking studies typically focus on the self-docking scenario, which is less practical in real applications. Moreover, some s
Post-agentic: Encouraging firms to use agentic tools (Claude Code/Lovable/N8N...) markedly improves startup growth & productivity. Pre-agentic: Encouraging firms to use a GPT4 advisor has uneven effec
arXiv:2512.22113v2 Announce Type: replace-cross Abstract: Unresolved production cloud incidents cost an average of over $2M per hour. This paper introduces PRAXIS, an orchestrator that manages and dep
arXiv:2511.16839v3 Announce Type: replace-cross Abstract: Heart failure (HF) discharge planning depends on identifying patients at risk of deterioration or death, yet accurate prediction from routinel
arXiv:2604.22882v1 Announce Type: new Abstract: Modern container ships face higher wind loads due to increased windage areas, making accurate predictions of wind loads essential for mooring design. Ex
arXiv:2604.23543v1 Announce Type: cross Abstract: Test-time alignment methods offer a promising alternative to fine-tuning by steering the outputs of large language models (LLMs) at inference time wit
arXiv:2604.24356v1 Announce Type: cross Abstract: What do recurrent neural networks, polynomial ODEs, and discrete polynomial maps each bring to computation, and what do they lack? All three operate o
arXiv:2602.11079v3 Announce Type: replace-cross Abstract: We propose probe-based data attribution, a method that traces behavioral changes in post-trained language models to responsible training datap