Knowledge catalogue
My feed has been hijacked this week by frontier model influencers who say they've had 5.6 Sol and Fable for 'months'. I think this tells an inaccurate story the field. From the outside it makes AI pro
arXiv:2607.06678v1 Announce Type: new Abstract: How can pretrained Vision-Language-Action (VLA) models retain long-horizon visual histories with high-frequency updates without sacrificing efficiency?
arXiv:2607.07083v1 Announce Type: cross Abstract: Subsampling significantly reduces the number of measurements, thereby streamlining data processing and transfer overhead, and shortening acquisition t
arXiv:2607.06612v1 Announce Type: cross Abstract: Federated Learning (FL) enables multiple clients to collaboratively train machine learning models while retaining data locality, thereby enhancing use
arXiv:2607.06597v1 Announce Type: cross Abstract: Public chest-radiograph (CXR) datasets are typically released with small, fixed label schemas such as CheXpert-14. However, the underlying free-text r
Long-context handling remains a core challenge for language models: even with extended context windows, models often fail to reliably extract, reason over, and use the information across long contexts
arXiv:2607.06889v1 Announce Type: cross Abstract: Deep learning image classifiers achieve strong predictive performance yet remain opaque in how decisions are formed. A model may predict correctly whi
arXiv:2607.07675v1 Announce Type: new Abstract: Despite the recent promise in robot control, video generative models suffer from a domain mismatch due to their primary focus on content creation. For e
arXiv:2607.07492v1 Announce Type: new Abstract: Many reasoning tasks are not well described by a single left-to-right chain: a solver may need to pursue a plausible branch, observe delayed failure, an
arXiv:2607.06948v1 Announce Type: cross Abstract: The accuracy of existing leaf-wood segmentation methods for tree point clouds varies across forest types and sites. Self-supervised learning (SSL) on
arXiv:2607.07019v1 Announce Type: new Abstract: Recent advances in semi-supervised medical image segmentation have achieved remarkable performance through prediction consistency, pseudo-label supervis
arXiv:2607.07467v1 Announce Type: new Abstract: Spatial and Single-cell transcriptomics are transformative in deciphering cellular dynamics. As the fundamental paradigm for reconstructing cell develop
arXiv:2607.07135v1 Announce Type: new Abstract: Contrastive Language-Image Pre-training (CLIP) relies on softmax-based self-attention, a strictly positive distribution that assigns probability mass to
spent a ton of time working on this!! so happy to see the results come out. very impressive model from @NVIDIAAI that we fit our harness to so we could get better performance! We tuned the harness for
arXiv:2607.07388v1 Announce Type: new Abstract: Large Language Models (LLMs) store factual knowledge and domain-specific patterns implicitly in dense Transformer parameters, making knowledge expansion
arXiv:2607.07500v1 Announce Type: cross Abstract: Time series classification (TSC) is dominated by a two-stage paradigm: train a feature encoder -- either from scratch on the target dataset or via pre
arXiv:2603.27742v2 Announce Type: replace Abstract: Vision-language agents that orchestrate specialized tools for image restoration (IR) have emerged as a promising method, yet most existing framework
arXiv:2607.07177v1 Announce Type: cross Abstract: Background: Automated 3D segmentation of muscles and adipose tissue from CT is vital for body composition analysis, but multi-source data heterogeneit
arXiv:2602.02712v2 Announce Type: replace-cross Abstract: A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, id
arXiv:2607.06779v1 Announce Type: new Abstract: Real-time stereo matching is crucial for robotics, autonomous systems, and embedded vision applications, where both computational efficiency and dispari
arXiv:2607.07099v1 Announce Type: new Abstract: Squint and cataract are major ocular disorders that majorly affect visual perception and interaction capability. This paper proposes a real-time video-b
arXiv:2510.13817v2 Announce Type: replace Abstract: The growth of IoT devices in shared environments has outpaced our ability to identify them, posing urgent risks to privacy, safety, and accountabili
arXiv:2506.19348v2 Announce Type: replace Abstract: Training-free motion customization imposes motion patterns from reference videos onto video generators through test-time computation. Most existing
arXiv:2607.07123v1 Announce Type: new Abstract: Segmenting slender curvilinear structures such as retinal vessels, cracks, and roads demands topological correctness, as even a single-pixel discontinui
arXiv:2510.17476v2 Announce Type: replace Abstract: Equitable access to reliable health information is vital when integrating AI into healthcare. Yet, information quality varies across languages, rais
arXiv:2607.06252v1 Announce Type: cross Abstract: Many problems in science and engineering are difficult to model accurately, either due to unknown physical mechanisms, poorly quantified measurement u
arXiv:2607.06291v1 Announce Type: new Abstract: Game worlds have traditionally been built through labor-intensive production pipelines, making them costly to develop, difficult to customization, and e
arXiv:2607.06413v1 Announce Type: cross Abstract: Large language model coding agents increasingly perform open-ended data modeling and analysis. These agents are stochastic and adaptive, and therefore
arXiv:2510.16165v2 Announce Type: replace Abstract: A key question in benchmarking generative crystal reconstruction models is how the amount and type of crystallographic information provided to a gen
arXiv:2607.05898v1 Announce Type: new Abstract: Evaluating whether unlearning algorithms truly remove training data influence remains an open challenge. We propose a practical auditor that computes da
arXiv:2607.05859v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are promising for construction-site monitoring, and recent construction-tailored VLMs have primarily adapted pretrained VL
The search results don't contain specific details about the b9914 release. Based on the context of llama.cpp releases, b9914 is a build/commit version in the llama.cpp project, an open-source tool for
arXiv:2607.05445v1 Announce Type: cross Abstract: Extended Reality (XR) wearables require always-on perception within tight power envelopes of a few watts and motion-to-photon latency budgets below 20
Box Agent uses @LangChain’s Deep Agents harness to bring specialized agents into the enterprise content platform.w @NVIDIA + LangChain’s work with Nemotron 3 Ultra reinforces where AI is headed: open,
arXiv:2606.22511v2 Announce Type: replace Abstract: In open-ended generation, LLMs frequently fall into the 'likelihood trap', marked by repetitive degeneration and vocabulary dullness, creating a dis
Busy couple days ahead! Today, @nvidia Nemotron 3 Ultra support for @LangChain Deep Agents at a fraction of the cost -w/ Quick Start Prompt Tomorrow is Wikimania🔥 @hwchase17 is chatting with with @Bra
arXiv:2604.05543v2 Announce Type: replace Abstract: Multivariate time series forecasting often struggles to capture long-range dependencies due to fixed lookback windows. Retrieval-augmented forecasti
Come help us scale @harvey’s model training team. If you’re interested in bringing frontier agent research into the Harvey product and working with: - @baseten to scale up RL to 80M+ token virtual dat
arXiv:2607.05790v1 Announce Type: new Abstract: Tool-augmented large language models extend their capabilities beyond parametric knowledge through external tools, but tend to invoke them unnecessarily
arXiv:2607.05849v1 Announce Type: new Abstract: Low-resource languages remain challenging for machine translation, and Mongolian is a representative case. As a digraphic language, Mongolian is written
arXiv:2607.06140v1 Announce Type: new Abstract: Large language model (LLM) agents require post-training methods that can improve long-horizon decision making from environment feedback. However, existi
arXiv:2607.05590v1 Announce Type: cross Abstract: Implantable brain-computer interfaces require on-node spike sorting to reduce telemetry bandwidth and power while maintaining reliable neural decoding
dcode <> nemotron 3 ultra <> OpenShell 🔥 Never been easier to own your agent IP! Introducing the NemoClaw Deep Agents Blueprint, a reference architecture for building open agent systems developed with
arXiv:2607.05439v1 Announce Type: new Abstract: Many all-atom generative protein models can in principle design large multimeric complexes by jointly modelling all chains, but their quadratic token- a
arXiv:2607.06565v1 Announce Type: cross Abstract: Unified 3D foundation models aspire to generate 3D assets and reason about them in language within a single backbone, but their text-3D interaction re
arXiv:2607.05457v1 Announce Type: cross Abstract: Deep neural networks often contain substantial hidden-state redundancy, but most compression methods operate directly on weights, neurons, or quantise
arXiv:2607.05933v1 Announce Type: cross Abstract: Dynamic Voltage Frequency Scaling (DVFS) on resource-constrained embedded GPU platforms is essential for energy-efficient small language model (SLM) f
arXiv:2607.06150v1 Announce Type: new Abstract: Reliable seam segmentation is essential for autonomous robotic welding in construction, where harsh illumination, specular reflections, and thin weld ge
Enterprises don’t just need agents that perform. They need agents they can shape, govern and improve as their business evolves. That’s the idea behind our work with LangChain. Read more: https://nvda.
arXiv:2607.05559v1 Announce Type: new Abstract: Foundation machine learning force fields (MLFFs) such as MACE-MP-0 and UMA cover broad chemical space at near density functional theory (DFT) accuracy.
Excited to team up with partners across the AI infrastructure + enterprise ecosystem. @EY_US @baseten @FireworksAI_HQ @nebiusai @CrusoeAI @DeepInfra @togethercompute Introducing the NemoClaw Deep Agen
arXiv:2607.05553v1 Announce Type: new Abstract: Transient stability control in smart grids requires rapid post-fault damping of generator frequency and rotor angle deviations to prevent cascading fail
arXiv:2607.05758v1 Announce Type: cross Abstract: Automated experimentation is moving from closed-loop optimization toward open decision-making, where human or AI planners must forecast the consequenc
arXiv:2607.05794v1 Announce Type: new Abstract: Long-term user memory is essential for personalized conversational agents, yet many memory systems still expose memory through passive retrieval interfa
arXiv:2308.16041v2 Announce Type: replace Abstract: Talking head generation has progressed rapidly from landmark- and GAN-based facial animation to diffusion models, neural rendering, 3D-aware avatars
arXiv:2607.06546v1 Announce Type: cross Abstract: Denoising graphs is a fundamental problem in graph learning and the core operation of graph diffusion models. Attention-based architectures like graph
arXiv:2607.06540v1 Announce Type: new Abstract: Developing seamless, high-performance, native intelligent full-duplex Spoken Language Models (SLMs) remains a critical challenge and long-standing goal
arXiv:2508.01725v5 Announce Type: replace-cross Abstract: Recent advances in continuous conditional generative modeling, including Continuous conditional Generative Adversarial Network (CcGAN) and Con
arXiv:2603.10254v2 Announce Type: replace Abstract: Synthetic tabular data generation addresses data scarcity and privacy constraints in a variety of domains. Tabular Prior-Data Fitted Network (TabPFN
Introducing the NemoClaw Deep Agents Blueprint, a reference architecture for building open agent systems developed with @NVIDIA ✅ A fully open stack enterprises can own and customize ✅ Benchmark-leadi