Knowledge catalogue
arXiv:2511.12373v2 Announce Type: replace-cross Abstract: In the field of medical imaging, AI-assisted techniques such as object detection, segmentation, and classification are widely employed to alle
arXiv:2609.23906v1 Announce Type: new Abstract: This paper introduces a novel algorithm for predicting conditional joint distributions of vector-valued targets in stochastic systems whose randomness i
arXiv:2211.01566v2 Announce Type: replace-cross Abstract: This paper presents the applications of scientific ray-tracing in modeling and simulating light transport for space-borne image data generatio
arXiv:2609.22774v1 Announce Type: new Abstract: This paper presents our system for Track 2 of the NLPCC 2026 Shared Task 10 on citation-level faithfulness in AI-assisted scientific reporting. Given an
arXiv:2609.22237v1 Announce Type: new Abstract: Merging low-rank adapters (LoRAs) promises to eliminate the overhead of swapping task-specific weights at inference time. However, existing merging meth
arXiv:2609.24517v1 Announce Type: cross Abstract: Model merging aims to combine multiple fine-tuned models derived from a common pretrained model into a single multi-task model without additional join
arXiv:2609.23856v1 Announce Type: new Abstract: Excessive force may damage tissue and increase the risk of anastomotic leakage in robotic colorectal surgery. Although the da Vinci 5 provides force sen
arXiv:2609.22133v1 Announce Type: new Abstract: In this paper, we show that LLM and human coding are observationally equivalent in terms of annotation quality: recent LLMs agree with expert coders at
arXiv:2609.24195v1 Announce Type: new Abstract: Reliable perception is essential for underwater vehicles operating in complex environments, where light attenuation and scattering often degrade visibil
arXiv:2609.22990v1 Announce Type: new Abstract: We study the symmetric and antisymmetric parts of bilinear forms in the attention heads of trained large language models. We introduce an orthogonally i
arXiv:2609.24504v1 Announce Type: new Abstract: Fine-tuned checkpoints and adapters now fill public repositories, and the most common operation applied to these artifacts is model merging: arithmetic
arXiv:2609.23819v1 Announce Type: cross Abstract: The Generalized Naive Bayes (GNB) model was introduced for discrete and categorical random variables as an extension of classic Naive Bayes. We now ac
arXiv:2604.01921v2 Announce Type: replace Abstract: Automotive radar perception pipelines commonly construct angle-domain representations via beamforming before applying learning-based models. This wo
arXiv:2609.22295v1 Announce Type: new Abstract: Event pipelines often discretize asynchronous timestamps before learning. This step looks harmless, but its stability depends directly on temporal resol
arXiv:2609.23686v1 Announce Type: new Abstract: Patch-based autoregressive time-series forecasting often ties input representation, learned transitions, and recursive execution to one patch length. We
arXiv:2609.23753v1 Announce Type: new Abstract: Generative world models aim to predict future states conditioned on actions, where action controllability is fundamental for reliable dynamics modeling.
arXiv:2609.24253v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3DGS) provides high-fidelity scenes for large-scale embodied simulation, but constructing large-scale urban assets remains cons
arXiv:2408.08823v2 Announce Type: replace Abstract: We develop a theoretical foundation for designing group-equivariant neural networks that align the choice of symmetries with the underlying probabil
arXiv:2609.23157v1 Announce Type: cross Abstract: Aerial Reconfigurable Intelligent Surfaces (ARISs) can enhance wireless connectivity in obstructed environments by combining reconfigurable metasurfac
arXiv:2609.24138v1 Announce Type: cross Abstract: Generative models have recently demonstrated considerable promise in speech super-resolution (SSR). Nevertheless, the majority of existing work has co
arXiv:2609.23574v1 Announce Type: cross Abstract: In high-dimensional tabular learning, feature screening provides a lightweight, model-agnostic way to remove irrelevant features before model fitting.
arXiv:2609.22687v1 Announce Type: new Abstract: We present PanoSeg3R, a feed-forward framework for 3D panoramic semantic segmentation. Unlike existing methods designed for perspective inputs, PanoSeg3
arXiv:2609.23551v1 Announce Type: new Abstract: Standard positional encodings represent position as a one-dimensional reading-order coordinate, but reading order alone does not determine hierarchical
arXiv:2609.23786v1 Announce Type: cross Abstract: This paper presents a partial-scan-and-move strategy for source seeking with a mobile robot equipped with an offset scalar sensor. At each robot posit
arXiv:2609.24116v1 Announce Type: new Abstract: Although deep learning has advanced Whole Slide Image (WSI) Analysis, tissue artifacts like bubbles and folds often cause silent failures by concealing
arXiv:2609.23495v1 Announce Type: new Abstract: Failures of high-resolution MLLMs are commonly attributed to a visual problem, motivating zooming, cropping, and related visual interventions to recover
arXiv:2609.22880v1 Announce Type: cross Abstract: LLM rerankers add of the order of $0.2-0.3 per 1,000 queries and about a second of tail latency on top of a graph-augmented dense pipeline such as Hip
arXiv:2609.22189v1 Announce Type: cross Abstract: The Schrodinger equation in one spatial dimension admits a small set of exactly solvable potentials that serve as natural proving grounds for any new
arXiv:2609.23549v1 Announce Type: new Abstract: Screening oxygen-evolution catalysts on combinatorial libraries requires deciding which candidates receive the remaining measurements. The deciding acti
arXiv:2609.24569v1 Announce Type: cross Abstract: Over the past decade, a growing body of research has shown that gamma-weak submodularity broadly arises in numerous subset selection tasks, including
arXiv:2602.09093v2 Announce Type: replace-cross Abstract: Computational discovery of magnetic materials remains challenging because magnetism arises from the competition between kinetic energy and Cou
arXiv:2609.23529v1 Announce Type: new Abstract: Neural operators have emerged as powerful surrogates for solving partial differential equations (PDEs), yet their reliability under distribution shift r
arXiv:2609.24524v1 Announce Type: new Abstract: Background: Microvascular invasion (MVI) predicts recurrence and survival in hepatocellular carcinoma (HCC) but requires postoperative histopathology fo
arXiv:2609.22963v1 Announce Type: new Abstract: This study develops a prescribed-time performance-shaping control method for curvature tracking of a single-segment flexible arm actuated by three antag
arXiv:2609.22607v1 Announce Type: new Abstract: We argue here that the current dominant practice in LLM human simulation: prompting instruction-tuned assistant language models to role-play personas, i
arXiv:2609.24397v1 Announce Type: new Abstract: The conventional testing process quickly fails when applied to ML-based systems such as obstacle detection in vehicles: if an obstacle is not detected i
arXiv:2609.23386v1 Announce Type: new Abstract: Text-guided 3D building generation holds tremendous application potential, yet existing generative models typically output inseparable single meshes or
arXiv:2609.22106v1 Announce Type: cross Abstract: Accuracy of Low-bit quantization of linear layers is often dominated by a small number of outliers. Although existing methods, such as smoothing, rota
arXiv:2609.23880v1 Announce Type: new Abstract: Temporal Information Retrieval (TIR) has been increasingly critical given the rise of Retrieval-Augmented Generation (RAG). Since temporally mismatched
arXiv:2609.23139v1 Announce Type: new Abstract: Most medical vision-language models (VLMs) excel at open-ended report generation and VQA but provide limited support for structured, fine-grained clinic
arXiv:2609.22122v1 Announce Type: new Abstract: Cross-device hardware evaluation often assumes that if architecture rankings transfer across devices, a proxy device can support target-side model selec
arXiv:2609.22135v1 Announce Type: new Abstract: Omni-modal large language models integrate text, audio, and image signals into a shared residual stream, where concepts such as emotion can be linearly
arXiv:2607.14293v2 Announce Type: replace-cross Abstract: Ionizing radiation from cosmic rays and gammas can induce discontinuous jumps in the environmental charge of superconducting qubits (charge ju
arXiv:2609.23141v1 Announce Type: cross Abstract: Real time plasma state estimation for control of Tokamak devices are challenging due to the stringent latency requirements of the plasma control syste
arXiv:2509.22650v3 Announce Type: replace Abstract: Most existing approaches to referring segmentation achieve strong performance only through fine-tuning or by composing multiple pre-trained models,
arXiv:2501.08547v2 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) have been widely adopted for their ability to compute expressive node representations in graph datasets. However,
arXiv:2609.24750v1 Announce Type: cross Abstract: The growing demand for real-time, data-driven decision-making in complex and dynamic systems is placing increasing pressure on traditional Operational
arXiv:2609.24158v1 Announce Type: new Abstract: Reconstructing expressive and relightable 3D head avatars from monocular videos remains challenging in computer vision, as it requires accurate modeling
arXiv:2512.09201v2 Announce Type: replace-cross Abstract: We introduce a framework for converting 3D shapes into compact and editable assemblies of analytic primitives, directly addressing the persist
arXiv:2609.23967v1 Announce Type: new Abstract: Diffusion models are increasingly adapted from generation to conditional prediction, where a conditioning signal is combined with an evolving noisy repr
arXiv:2609.22506v1 Announce Type: new Abstract: Vision Transformers allocate most parameters to multi-layer perceptrons (MLPs) for channel mixing, while token interactions usually rely on quadratic mu
arXiv:2609.23409v1 Announce Type: new Abstract: Cache-based test-time adaptation improves CLIP predictions by storing and retrieving examples from the target stream while keeping the model frozen. How
arXiv:2609.24850v1 Announce Type: new Abstract: Computing accurate geometry from multi-view images is a fundamental problem in computer vision. Recent feed-forward (FF) models jointly estimate 3D geom
arXiv:2609.22547v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) often improves pass@1 while falling behind its base model at larger sampling budgets k, a crosso
arXiv:2609.24413v1 Announce Type: new Abstract: In this work, we propose a haptic update control law that uses reaction torques to correct axial misalignment during robotic valve manipulation. Unlike
arXiv:2609.22167v1 Announce Type: new Abstract: Predicting reaction yield from molecular structure and reaction context can cut experimental trial-and-error and speed up condition screening in synthet
arXiv:2502.06726v4 Announce Type: replace-cross Abstract: We derive first-order Pontryagin optimality conditions for stochastic optimal control with deterministic controls for systems modeled by rough
arXiv:2609.23466v1 Announce Type: new Abstract: Long-running LLM agents require memory that persists and evolves across sessions. Text-based memory retrieves and reconstructs past interactions at ever
arXiv:2609.23450v1 Announce Type: new Abstract: Accurate cue-ball identification is essential for metric analysis of broadcast snooker. Existing systems evaluate each candidate independently against a
arXiv:2609.22834v1 Announce Type: new Abstract: Open-vocabulary semantic segmentation (OVS) of remote sensing imagery is a challenging pixel-level task requiring strong generalization and adaptation t