Knowledge catalogue
CUDA: MMVQ nwarps=8 for bs=1 for dense models on DGX Spark Signed-off-by: ynankani ynankani@nvidia.com skip moe experts and allow others based on k geometry (allow only small idle tail) Signed-off-by:
arXiv:2608.14635v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly trained with reinforcement learning in long-horizon, sandboxed environments. Unlike conventional RL
arXiv:2608.15108v1 Announce Type: cross Abstract: Large language model agents are increasingly connected to high-value resources such as computing infrastructure, credentials, usage budgets, identitie
arXiv:2608.15710v1 Announce Type: cross Abstract: We address a fundamental gap in 3D-LLMs: existing models focus on single-object/scene description, struggling with detailed, inter-object comparison.
arXiv:2608.15772v1 Announce Type: new Abstract: When a language model refuses to answer a prompt, it is unclear whether the correct answer is erased from its internal representations, or merely suppre
arXiv:2608.15574v1 Announce Type: cross Abstract: Video question answering systems built on vision-language models often produce timestamped claims with high confidence even when unsupported by the ci
arXiv:2608.15843v1 Announce Type: cross Abstract: Characterising electrophysiological properties of cardiac tissue efficiently and accurately from spatially sparse intracardiac measurements is clinica
arXiv:2602.12756v2 Announce Type: replace Abstract: Large Language Models (LLMs) have recently shown exceptional potential in time series forecasting (TSF), leveraging their inherent sequential reason
arXiv:2608.15972v1 Announce Type: cross Abstract: Synchronized camera and wireless measurements observe the same scene through different physical channels. The central difficulty is that a representat
arXiv:2511.11427v2 Announce Type: replace Abstract: Referring Expression Comprehension (REC) requires models to localize objects in images based on different types of natural language descriptions. Ev
arXiv:2608.15698v1 Announce Type: new Abstract: Visual document retrieval is a critical component of multimodal retrieval-augmented generation, aiming to identify query-relevant pages from document co
arXiv:2608.16870v1 Announce Type: new Abstract: Accurate classification of circulating tumor cell (CTC) phenotypes can provide valuable information for assessing metastatic potential. Label free micro
arXiv:2608.15213v1 Announce Type: new Abstract: Crowd counting must recover reliable local density under severe variations in perspective, head scale, occlusion, and background clutter. Although moder
arXiv:2608.16221v1 Announce Type: new Abstract: Reliable gas source localization (GSL) is critical to safety in industrial and urban environments, yet remains challenging indoors because walls and obs
arXiv:2608.14600v1 Announce Type: cross Abstract: We present a demonstration for generative multicasting with on-device, intent-aware semantic decomposition. At the transmitter, DNN-based segmentation
arXiv:2608.15019v1 Announce Type: cross Abstract: Breast mass segmentation is an important step in computer-aided mammography, but it remains difficult because masses can have low contrast, irregular
arXiv:2608.15502v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as a promising foundation for Embodied AI, but their high inference cost poses significant challenges f
arXiv:2608.15614v1 Announce Type: cross Abstract: The use of multimodal LLMs (MLLMs) for egocentric video understanding with wearable devices is constrained by the token budget. Memory and compute cos
arXiv:2509.04899v4 Announce Type: replace-cross Abstract: Restricted Boltzmann machines (RBMs) are energy-based models originating from statistical physics, in which hidden units mediate the probabili
arXiv:2302.12177v4 Announce Type: replace-cross Abstract: Predicting the binding sites of target proteins plays a fundamental role in drug discovery. Most existing deep-learning methods consider a pro
arXiv:2608.15749v1 Announce Type: new Abstract: Existing 3D editing methods have made notable progress in controllability, yet they remain limited in several important ways. Most approaches rely on te
arXiv:2608.16295v1 Announce Type: new Abstract: AI coding agents need more than relevant snippets: they need business semantics, validation evidence, relations, and assurance that their context is cur
arXiv:2608.14654v1 Announce Type: cross Abstract: Federated Learning (FL) is a collaborative paradigm that enables multiple devices to train a global model while preserving local data privacy. A major
arXiv:2603.17555v2 Announce Type: replace-cross Abstract: Diffusion-based image-to-video (I2V) models are increasingly effective, yet they struggle to scale to ultra-high-resolution inputs (e.g., 4K).
arXiv:2608.16002v1 Announce Type: cross Abstract: Reliable uncertainty quantification (UQ) is essential for deploying large language model (LLM) agents in complex interactive environments. Existing UQ
arXiv:2608.15517v1 Announce Type: new Abstract: Chain-of-thought reasoning has substantially improved the problem-solving capabilities of multimodal large language models. Fine-grained visual evidence
arXiv:2608.15107v1 Announce Type: new Abstract: Federated learning (FL) is a practical framework that can train models on distributed user data while guaranteeing data privacy; however, due to heterog
arXiv:2608.16733v1 Announce Type: cross Abstract: Physical design algorithms operate within tightly coupled, multi-stage optimization flows, where stage-local gains may vanish or induce downstream deg
arXiv:2608.16328v1 Announce Type: new Abstract: Instruction-based general video editing seeks to unify diverse editing operations within a single, intuitive interface. Existing approaches often rely o
arXiv:2608.15647v1 Announce Type: cross Abstract: Semantic segmentation of very-high-resolution (VHR) remote sensing imagery increasingly benefits from strong pretrained hierarchical encoders, yet exp
arXiv:2511.21317v2 Announce Type: replace Abstract: The Visual Geometry Grounded Transformer (VGGT) marks a significant leap forward in 3D scene reconstruction, as it is the first model that directly
arXiv:2608.16607v1 Announce Type: new Abstract: Whole-slide image (WSI) analysis remains computationally challenging due to the extremely large spatial resolution of slides and the sparse distribution
I was checking out benchmarks of this model and apparantly better than Qwen3.5 9b reasoning across the bench on artificial analysis. I have used the 9b model for variety of stuff and it has been amazi
arXiv:2608.15693v1 Announce Type: new Abstract: Running large AI models on resource-constrained edge devices requires model compression to reduce model size and computation. What compresses well, howe
arXiv:2608.16185v1 Announce Type: cross Abstract: LLM agents increasingly answer questions over dynamic raw-document collections, where files may change before preprocessing, and relevant evidence (sp
arXiv:2608.14625v1 Announce Type: cross Abstract: Academic peer review is under mounting strain: NeurIPS 2025 received 21,575 submissions, ICLR 2025 received 11,603, and ICML 2025 received 12,107. Thi
I have a lot of content in my personal Obsidian vault and would feel much more comfortable using LLMs with an offline model. I've experimented with Ollama and various small 3b/8b local models (given c
arXiv:2608.16429v1 Announce Type: new Abstract: Foundational models for tabular data have made significant progress in recent years, with TabICLv2 reporting state-of-the-art performance on several tab
arXiv:2608.15156v1 Announce Type: cross Abstract: World models may predict the future without making clear which parts of their hidden state actually drive those predictions. We ask whether a small, d
arXiv:2411.15041v2 Announce Type: replace Abstract: Advanced Multimodal Large Language Models (MLLMs) struggle with recent Knowledge-based Visual Question Answering (VQA) tasks, such as INFOSEEK and E
arXiv:2608.16201v1 Announce Type: new Abstract: Multimodal sentiment analysis (MSA) aims to predict sentiment polarity and intensity from heterogeneous inputs such as text, audio, and vision. While la
The AI wants to run a higher risk action. Nyx AI stops it here. Nyx AI deliberately invokes a native Windows confirmation before certain higher risk actions can continue. The model cannot approve this
arXiv:2608.16070v1 Announce Type: cross Abstract: Reliable global ocean forecasting is critical for climate monitoring, marine navigation, and extreme event early warning. Physics-based ocean forecast
arXiv:2608.14677v1 Announce Type: cross Abstract: Most mobile image-generation applications are thin clients over cloud services, leaving outputs hard to audit. We present an Android latent-diffusion
arXiv:2608.15267v1 Announce Type: new Abstract: Semantic change detection (SCD) is a bitemporal dense-prediction task that jointly identifies changed regions and their semantic states before and after
arXiv:2608.14557v1 Announce Type: cross Abstract: Low Earth Orbit (LEO) computing is emerging for low-latency, globally distributed AI services, enabled by advances in satellite constellations and reu
arXiv:2608.14774v1 Announce Type: new Abstract: Modern sequence models heavily rely on massive memory footprints and large-batch stochastic optimization, barriers that restrict sample efficiency and c
arXiv:2608.15026v1 Announce Type: new Abstract: Post-training of vision-language-action (VLA) models typically relies on expert demonstrations and policy interaction trajectories. However, in long-hor
arXiv:2608.16477v1 Announce Type: new Abstract: AI-RAN brings large language model (LLM) serving close to mobile users, but cellular handover can separate an active request from its inference state: t
arXiv:2608.15115v1 Announce Type: new Abstract: Adversarial examples generated on a surrogate deep neural network (DNN) can often successfully fool other black-box DNN models. This cross-model transfe
arXiv:2602.08261v2 Announce Type: replace Abstract: Auto-bidding systems strive to maximize marketing value while maintaining high compliance with efficiency constraints, such as Target Cost-Per-Actio
arXiv:2608.16167v1 Announce Type: cross Abstract: High-precision radio map construction is essential for emerging 6G Integrated Sensing and Communication (ISAC) applications, including digital twins a
arXiv:2509.12757v2 Announce Type: replace Abstract: Cross-view object geo-localization (CVOGL) aims to determine the location of a specific object in high-resolution satellite imagery given a query im
arXiv:2608.14991v1 Announce Type: new Abstract: Cloud-hosted vision-language models (VLMs) offer greater contextual reasoning capabilities than smaller onboard models, but frequent visual uploads incr
arXiv:2608.15946v1 Announce Type: new Abstract: Rerouting the tendon path in tendon driven continuum manipulators (TDCMs) enables a broad range of deformation modes. This work presents a Reconfigurabl
arXiv:2608.14682v1 Announce Type: new Abstract: Real-world time series inherently intertwine global periodic structures with localized non-stationary variations. Existing approaches process these hete
arXiv:2608.15075v1 Announce Type: new Abstract: RS-LVLMs have advanced multimodal understanding of Earth observation imagery, yet their performance is fundamentally constrained by high-resolution proc
arXiv:2606.19888v2 Announce Type: replace-cross Abstract: Modeling long-sequence medical time series data, such as electrocardiograms (ECG), poses significant challenges due to high sampling rates, mu
arXiv:2608.15958v1 Announce Type: new Abstract: Deciding whether a Sokoban puzzle is solvable is PSPACE-complete (Culberson, 1997): solutions can be exponentially long and there is no short certificat
arXiv:2608.14922v1 Announce Type: cross Abstract: Mechanistic interpretability has recently expanded to Vision Transformers (ViTs), with Sparse Autoencoders (SAEs) increasingly used as post-hoc tools