Knowledge catalogue
arXiv:2610.08179v1 Announce Type: new Abstract: Text-driven 3D Gaussian editing commonly does not distinguish the editing reliability of rendered views, although different viewpoints provide supervisi
arXiv:2610.07080v1 Announce Type: new Abstract: Attention maps are often interpreted as evidence of what a forecasting model uses when making predictions. In our load-forecasting model, a CLS represen
arXiv:2610.06877v1 Announce Type: cross Abstract: Accurate prediction does not establish that a world model has recovered a physical law: distinct dynamics can generate identical records under the sam
arXiv:2610.08718v1 Announce Type: new Abstract: Knowledge that a language model appears to forget during finetuning often remains stored and can be recovered, a phenomenon called spurious forgetting.
arXiv:2610.07715v1 Announce Type: cross Abstract: A memory system can retire an obsolete value and later restore it merely because the same old statement appears again. A re-read of an old source and
arXiv:2610.07018v1 Announce Type: new Abstract: Vision-language models (VLMs) have achieved strong performance in multimodal reasoning, yet they remain prone to generating plausible but incorrect answ
arXiv:2609.33155v2 Announce Type: replace Abstract: Test-time scaling and post-training have improved LLM performance in coding and mathematical reasoning, but their effectiveness for individual stanc
arXiv:2610.08165v1 Announce Type: new Abstract: The mechanical properties of a metallic alloy are set by its microstructure and texture: the size and shape of its grains and the orientation of their c
arXiv:2610.07553v1 Announce Type: cross Abstract: LoRA fine-tuning adapts small language models (SLMs) to heterogeneous instruction data within a low-rank update subspace, making it vulnerable to thre
arXiv:2610.08502v1 Announce Type: cross Abstract: Proactive power management systems reduce processor dynamic power through runtime power prediction and power-aware scheduling. Accurate, stable and lo
arXiv:2601.12966v2 Announce Type: replace-cross Abstract: The Lombard effect plays a key role in natural communication, particularly in noisy environments or when addressing hearing-impaired listeners
arXiv:2610.04022v1 Announce Type: new Abstract: Powered neck exoskeletons are developed to restore head-neck motions for those with neck muscle weakness. Current methods using hand-held input devices
arXiv:2610.05130v1 Announce Type: cross Abstract: An electromagnetic inversion scheme that integrates stochastic optimization (STO) and plug-and-play (PNP) regularization into contrast-source inversio
arXiv:2610.06508v1 Announce Type: new Abstract: Illuminant estimation is a fundamental problem in computational photography, as it enables the correction of color shifts induced by varying lighting co
arXiv:2610.04939v1 Announce Type: new Abstract: We ask whether physically meaningful correspondences discovered inside a trained scientific model remain meaningful outside the conditions under which t
arXiv:2610.04256v1 Announce Type: new Abstract: Exactly computing the maximum function is a standard test case for studying depth in ReLU networks. Two hidden layers are known to suffice for up to twe
arXiv:2610.04368v1 Announce Type: new Abstract: Extreme winter weather has repeatedly disrupted gas-fired power generation in the United States, yet the plant-level data needed to systematically quant
arXiv:2507.18104v3 Announce Type: replace Abstract: Brain encoding models predict time-resolved neural activity from computational representations of ongoing experience, providing a principled framewo
arXiv:2610.06464v1 Announce Type: new Abstract: As technology scales to smaller nodes, increasing current densities make electromigration (EM) one of the dominant reliability challenges in on-chip int
arXiv:2610.06798v1 Announce Type: cross Abstract: Machine-learning emulators of chaotic and stochastic systems are usually validated on forecast skill and long-run statistics. Neither certifies that a
arXiv:2610.06701v1 Announce Type: cross Abstract: A recurring design principle in modern optimizers is to decouple update magnitude from the raw gradient norm, yet its consequences for learning-curve
arXiv:2610.05413v1 Announce Type: new Abstract: Evaluating vision encoders requires metrics that reliably predict their downstream performance in multimodal large language models (MLLMs). Although rec
arXiv:2610.05794v1 Announce Type: cross Abstract: We develop and test a theory of language model representations in which there exist atomic features. Our main theoretical insight is that in such a mo
arXiv:2610.05758v1 Announce Type: new Abstract: Holes in LiDAR scans of environments with glass windows remain an unresolved problem in three-dimensional reconstruction. This study presents a pipeline
arXiv:2006.08426v5 Announce Type: replace-cross Abstract: Descent directions are fundamental to first-order methods for constrained convex optimization. In this work, we provide a unified perspective
arXiv:2610.03896v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used for automated algorithm design. However the computational cost of evaluating the generated algorithms
arXiv:2508.06084v3 Announce Type: replace Abstract: Vision-language models (VLMs) have achieved impressive performance on multimodal inference tasks, but the cost remains a significant challenge due t
arXiv:2610.04391v1 Announce Type: new Abstract: Vision-language-action policies may predict a transferable manipulation strategy yet fail to realize it reliably on the encountered object: objects comp
arXiv:2603.13790v2 Announce Type: replace Abstract: Data selection for language models is often framed as balancing example quality and diversity. We argue that both are consequences of a more fundame
arXiv:2610.05558v1 Announce Type: new Abstract: The Dobrushin coefficient of each attention-rollout factor satisfies kappa(frac12(I+A))lefrac12(1+kappa(A)), and multiplying these inequalities over lay
arXiv:2610.06094v1 Announce Type: new Abstract: Cone-beam computed tomography (CBCT) is widely used in image-guided radiotherapy, but scatter, beam hardening, noise, truncation, and other artifacts li
arXiv:2610.06135v1 Announce Type: new Abstract: Engineering design often starts from a 2D sketch that fixes style and proportions, yet the subsequent 3D shape optimization relies on learned generative
arXiv:2610.06180v1 Announce Type: new Abstract: Whether a time-series pattern is anomalous often depends on the operating regime of the monitored process. A missing event can signal a fault in one reg
arXiv:2610.04346v1 Announce Type: new Abstract: This paper proposes any-scale object detection using arbitrary-scale super-resolution for continuously rescaling object images, while general multi-scal
arXiv:2610.04058v1 Announce Type: cross Abstract: In this paper we use machine learning methods to predict radiation damage in the lead tungstate crystals of the CMS electromagnetic calorimeter at the
arXiv:2610.05143v1 Announce Type: new Abstract: Reinforcement learning (RL) policies can deteriorate under out-of-distribution (OOD) magnitude shifts. Starting from soft actor-critic (SAC) and its Bay
arXiv:2610.06443v1 Announce Type: new Abstract: The high cost of functional molecular assays, and prevalence of missing modalities and unmatched samples in computational biology, create significant ba
arXiv:2610.04051v1 Announce Type: new Abstract: Accurate early screening for Autism Spectrum Disorder (ASD) is a precursor to timely intervention, which is critical for improving cognitive and behavio
arXiv:2610.04342v1 Announce Type: cross Abstract: Inter-robot communication is a key enabling technology in cooperative robotics applications. While wireless communication is ubiquitous, simple, and e
arXiv:2610.04240v1 Announce Type: cross Abstract: For ground robots operating in outdoor environments, understanding the properties of the underlying terrain is essential for ensuring reliable operati
arXiv:2610.05409v1 Announce Type: new Abstract: Action-conditioned time-series forecasting requires accounting for how future actions and exogenous forcings influence multiple targets through partiall
Ben Affleck reveals he writes Python, understands convolutional neural networks, worked extensively with GPUs, and used his celebrity status to get private looks at Google and OpenAI’s video models “I
arXiv:2610.03720v1 Announce Type: cross Abstract: Continuous colormaps are widely used to visualize scalar fields, and their quality is typically evaluated using measures such as discriminative power
arXiv:2610.04931v1 Announce Type: new Abstract: This paper introduces a real-time thumbnail optimization system deployed at a global O(B) scale on a major short-form video platform. Unlike traditional
arXiv:2610.05040v1 Announce Type: new Abstract: Mapping post-harvest burned cropland is difficult when fires are small and fragmented and reliable labels are scarce. We developed a calibrated weak-sup
arXiv:2610.06035v1 Announce Type: new Abstract: Recovering geometry, materials, and lighting from photographs is highly ambiguous when only static illumination is available. Active-lighting setups red
arXiv:2610.04199v1 Announce Type: new Abstract: A robotic microscope watching living cells cannot afford to look as often as it would like. Every volume it acquires costs photons the specimen does not
arXiv:2610.06260v1 Announce Type: new Abstract: Diffusion transformers (DiTs) achieve state-of-the-art image generation, but their sampling cost limits deployment. Quantizing both weights and activati
arXiv:2610.04357v1 Announce Type: new Abstract: We give checkable positive-definiteness criteria for the limiting neural tangent kernel (NTK) and high-probability finite-width gradient-descent guarant
arXiv:2610.06687v1 Announce Type: new Abstract: While existing camera-controllable video generation models can produce visually compelling sequences, preserving intrinsic 4D spatiotemporal coherence r
arXiv:2610.05411v1 Announce Type: new Abstract: Motion capture data is rarely directly usable, as they typically exhibit missing segments, jitter, drift and contact artifacts. Traditionally, corrupted
arXiv:2610.06138v1 Announce Type: new Abstract: Graph Convolutional Networks (GCNs) have emerged as a powerful framework for learning from graph-structured data, yet their deployment on resource-const
arXiv:2610.05324v1 Announce Type: cross Abstract: Partnered human-humanoid interaction couples locomotion with continuous physical contact. A humanoid needs to coordinate with a person's motion while
arXiv:2610.05936v1 Announce Type: cross Abstract: One of the major transformative factors in 6G will be the integration of Artificial Intelligence (AI) to become a native part of Radio Access Network
arXiv:2610.05332v1 Announce Type: new Abstract: This paper tackles visible challenges in deep ensemble learning, where deep neural networks serve as ensemble members: training and storage burdens, and
arXiv:2610.04680v1 Announce Type: new Abstract: Summary: The single-cell gel electrophoresis ('comet') assay is a widely used technique for quantifying DNA damage at the individual cell level. However
arXiv:2610.06520v1 Announce Type: new Abstract: Neurons of the brain exhibit a rich repertoire of electrophysiology dynamics with the same repeated stimulus eliciting very different voltage responses
arXiv:2610.04143v1 Announce Type: new Abstract: Most feature-based choice models, classical and deep, score items and apply a single softmax. We introduce consideration circuits (CC), feature-based mo
arXiv:2610.05154v1 Announce Type: new Abstract: Geostationary satellite observations are important for wildfire detection and monitoring. The current study evaluates machine learning models for MTG FC
arXiv:2412.18539v3 Announce Type: replace-cross Abstract: Recent advances in statistical learning theory have revealed profound connections between mutual information (MI) bounds, PAC-Bayesian theory,