Knowledge catalogue
arXiv:2608.22583v1 Announce Type: cross Abstract: Clinical records contain rich evidence about patient state, but converting that evidence into reliable, structured knowledge graphs remains difficult
arXiv:2504.09421v3 Announce Type: replace-cross Abstract: Recent advances in reasoning with large language models (LLMs)has shown remarkable reasoning capabilities in domains such as mathematics and c
arXiv:2606.09590v2 Announce Type: replace Abstract: Medical language models (LMs) can memorize and reproduce protected health information, but privacy evaluations often focus on recovery of training t
arXiv:2608.22003v1 Announce Type: new Abstract: Data-Free Knowledge Distillation (DFKD) preserves privacy by transferring knowledge without real data access. However, existing generator-based DFKD met
arXiv:2608.21976v1 Announce Type: new Abstract: Agentic AI has automated parts of scientific discovery, including paper generation, expert-level coding, therapeutic proposal, and autonomous experiment
arXiv:2608.22967v1 Announce Type: new Abstract: Practical molecular inverse design is rarely a one-shot generation problem; it often takes the form of closed-loop candidate-pool enrichment, where unde
arXiv:2510.16927v2 Announce Type: replace Abstract: The optimization landscape of Transformer models remains poorly understood despite their widespread adoption. While recent studies have derived curv
arXiv:2608.21457v1 Announce Type: new Abstract: Unmanned aerial vehicle (UAV) object detection is critical for applications such as target search, where accurate detection of small objects in complex
arXiv:2608.22610v1 Announce Type: new Abstract: Agent skills, structured artifacts distilled from interaction trajectories and dynamically reused from skill banks, have become a central mechanism for
arXiv:2608.23011v1 Announce Type: cross Abstract: Graph-based retrieval-augmented generation (RAG) provides a scalable paradigm for long-video understanding, but existing systems typically inherit a f
arXiv:2608.23205v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have revolutionized reasoning in LLMs, and the increasing public availability of reasoning traces creates valuable opportu
arXiv:2511.22281v2 Announce Type: replace Abstract: Observing certain patches in an image reduces the uncertainty of others. Their realization lowers the distribution entropy of each remaining patch f
arXiv:2608.22064v1 Announce Type: new Abstract: We present our solution for the MOSEv2 track of the 8th Large-scale Video Object Segmentation (LSVOS) Challenge at ECCV 2026. The challenge evaluates ro
arXiv:2608.21464v1 Announce Type: cross Abstract: We demonstrate that structured distortion of training data - which we term complexity induction - can induce compositional generalization in a standar
arXiv:2608.21418v1 Announce Type: new Abstract: Manufacturing knowledge graphs that integrate data from heterogeneous industrial systems face a trust deficit: consumers cannot determine whether querie
arXiv:2608.22762v1 Announce Type: new Abstract: Knowledge graph question answering (KGQA) is a key task for evaluating KG-augmented Large Language Models (LLMs), and complex KGQA that requires multi-h
Compute has always been core to the @VerneRobotics story. Getting there meant negotiating long, expensive contracts with big neoclouds, and projecting compute needs years into the future. Verne wasn't
arXiv:2608.22930v1 Announce Type: new Abstract: Agentic AI is a fascinating new tool for software development. It is a huge step forward compared to 'conventional' AI assisted coding, which in turn wa
arXiv:2411.09686v4 Announce Type: replace-cross Abstract: Regressing a function F on R^d without incurring the statistical and computational curse of dimensionality requires exploitable structure. Com
arXiv:2608.23153v1 Announce Type: new Abstract: In high-stakes healthcare applications, machine learning models are frequently trained on data from one patient population and deployed on another, crea
arXiv:2608.21485v1 Announce Type: new Abstract: Physical Cell Identity (PCI) assignment is essential for interference management in dense 5G networks. As cellular networks scale, PCI reuse becomes una
arXiv:2608.21914v1 Announce Type: new Abstract: We align three upper ontologies that sit under UK and NATO defence data infrastructure: the Information Exchange Standard (IES), the Higher Quality Data
arXiv:2608.21441v1 Announce Type: cross Abstract: Automated training of surgeons is one of the most crucial factors that significantly minimize surgical training risks and expenses. With recent advanc
arXiv:2608.22100v1 Announce Type: new Abstract: Construction robotics and automation offer promising means of improving productivity, alleviating workforce shortages, and reducing workers' exposure to
arXiv:2608.21690v1 Announce Type: new Abstract: LLM agents increasingly take on long-running tasks whose history grows far beyond a single model context window. Existing approaches compress earlier in
arXiv:2608.22367v1 Announce Type: new Abstract: Diffusion multimodal large language models (dMLLMs) frequently produce long-form outputs marred by semantic drift and repetition, with quality generally
arXiv:2608.22679v1 Announce Type: new Abstract: Semantic segmentation has rapidly advanced with deep learning; however, challenges remain in effectively capturing local and global contexts as well as
arXiv:2602.17174v3 Announce Type: replace-cross Abstract: Robust control of mechanical systems with multiple uncertainties remains a fundamental challenge, particularly when nonlinear dynamics and ope
arXiv:2608.22533v1 Announce Type: new Abstract: Autonomous computer-use agents are increasingly applied to long-horizon tasks requiring coordinated application calls, persistent state tracking, and ve
arXiv:2608.22804v1 Announce Type: new Abstract: Real-world time-series classification tasks often exhibit class imbalance, which can be extremely severe in some applications. To avoid training biased
arXiv:2608.23343v1 Announce Type: new Abstract: Image acquisition with a camera involves several degradations due to the optical system, sensor, or low-level processing steps. We address blind deblurr
arXiv:2608.23551v1 Announce Type: cross Abstract: Recent advances in continuous diffusion and flow-based language models (LMs) have achieved performance competitive with discrete LMs. However, existin
arXiv:2608.21821v1 Announce Type: new Abstract: When Wikipedia's language editions describe the same concept, how differently do they frame it? Prior work measures coverage gaps between editions; we m
arXiv:2509.12811v2 Announce Type: replace Abstract: Large Language Models (LLMs) have shown remarkable prowess in text generation, yet producing long-form, factual documents grounded in extensive exte
arXiv:2608.23526v1 Announce Type: new Abstract: World models can predict video without learning dynamics that they reliably preserve. We test whether a frozen DreamerV3 trained only on pendulum video
arXiv:2608.23152v1 Announce Type: new Abstract: Counterspeech effectively neutralizes the impact of online hate. Although prior work explores automated counterspeech generation, it largely emphasizes
arXiv:2608.21740v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models are typically trained with behavior cloning (BC) on expert demonstrations. However, BC provides only positive superv
arXiv:2608.22221v1 Announce Type: new Abstract: We study counterfactual protocol evaluation: whether data collected under a realised observation protocol determine the predictive value of alternatives
arXiv:2608.22092v1 Announce Type: new Abstract: Reinforcement-learning models commonly predict complete future states, observations, or feature occupancies, even though action selection depends only o
arXiv:2608.23164v1 Announce Type: cross Abstract: Counterfactual (CF) explanations for time-series classifiers are usually evaluated one example at a time: what minimal edit flips this single window's
arXiv:2608.23244v1 Announce Type: cross Abstract: Large language models (LLMs) often produce fluent but incorrect answers with unwarranted confidence. A central limitation is that standard LLMs repres
arXiv:2608.23391v1 Announce Type: cross Abstract: Structured data exists in many forms (tables, knowledge graphs, charts, and time series), and converting it into text may involve different generation
arXiv:2608.23390v1 Announce Type: cross Abstract: English Wikipedia is often treated as the default encyclopedic source, yet non-English Wikipedia editions can contain richer locally grounded informat
arXiv:2608.22420v1 Announce Type: cross Abstract: Decoding perceived speech from non-invasive brain recordings has garnered significant attention in recent years due to its wide range of potential app
arXiv:2608.22074v1 Announce Type: cross Abstract: Identifying atomic defects at elevated temperature is difficult because thermal fluctuations blur the local symmetry that both geometric heuristics an
arXiv:2411.05625v2 Announce Type: replace-cross Abstract: We propose a new approach to falsify causal discovery algorithms without ground truth, which is based on testing the causal model on a variabl
arXiv:2607.27836v2 Announce Type: replace Abstract: Large language model unlearning is consistently fragile under relearn attacks. On TOFU, fine-tuning on twenty forget examples substantially recovers
arXiv:2608.22059v1 Announce Type: cross Abstract: Pretrained image encoders are central to medical image classification, where expert annotation is costly and task-specific cohorts are often limited.
arXiv:2608.22115v1 Announce Type: new Abstract: Collaborative multimodal inference improves edge perception by combining observations from distributed sensing devices, but transmitting high-dimensiona
arXiv:2608.22983v1 Announce Type: new Abstract: Robot manipulators are commonly engineered around a decoupled motion-generation stack: a planner computes a collision-free path and a lower-level contro
CUDA Python 1.0, released alongside CUDA 13.3, provides NVIDIA-maintained libraries and tools that expose the entire CUDA platform directly to Python through a single shared foundation. It adopts sema
arXiv:2608.23065v1 Announce Type: cross Abstract: Cultural understanding in video means more than recognizing what is visible; it requires grasping the symbolic and temporal significance of cultural c
arXiv:2608.23181v1 Announce Type: cross Abstract: As large language models (LLMs) continue to advance in coding capabilities, their potential in cybersecurity has drawn increasing research attention,
arXiv:2608.21462v1 Announce Type: cross Abstract: Due to the selection of their training data, large language models (LLMs) perform best on standard-language inputs from languages using the Latin alph
arXiv:2608.21529v1 Announce Type: cross Abstract: Timely and accurate assessment of property damage is critical following natural disasters. Traditional on-site inspections are labor-intensive, costly
Data center power startup Emerald AI Inc. today said that it has raised 150 million in new funding in an oversubscribed round at a valuation of 1.05 billion. Emerald will put the money into scaling up
arXiv:2603.00604v2 Announce Type: replace Abstract: High-quality pixel-level annotations are essential for the semantic segmentation of remote sensing imagery. However, such labels are expensive to ob
arXiv:2608.21584v1 Announce Type: new Abstract: We introduce a large language model (LLM)-driven approach for generating dynamic algorithmic dispatch heuristics in high-performance linear algebra. By
arXiv:2608.22361v1 Announce Type: cross Abstract: Finite datasets can share the same size and low-order statistics while differing strongly in structural complexity. We connect this dataset complexity
arXiv:2608.22277v1 Announce Type: new Abstract: Deep learning surrogates for forecasting chaotic dynamical systems suffer from catastrophic error accumulation over long-term autoregressive rollouts. T