Knowledge catalogue
arXiv:2610.14862v1 Announce Type: new Abstract: Machine learning models for protein-ligand interactions commonly rely on atomic coordinates, which are constructed by fitting molecular models to experi
arXiv:2610.17412v1 Announce Type: new Abstract: Vision Transformers incur high computational costs when processing long visual token sequences. Existing reduction methods typically rank tokens indepen
arXiv:2509.02003v2 Announce Type: replace Abstract: Markov chain Monte Carlo is one of the most useful tools for obtaining samples from complex distributions, such as posterior distributions in Bayesi
arXiv:2610.15453v1 Announce Type: cross Abstract: Neural audio codecs achieve remarkable performance but operate as closed ecosystems with rigidly co-trained encoderdecoder pairs, severely hindering i
arXiv:2610.18658v1 Announce Type: new Abstract: Generative models are often required to serve many downstream conditional tasks. In the training-free setting, a pretrained unconditional model is reuse
arXiv:2610.14935v1 Announce Type: new Abstract: Pipeline parallelism has become a critical technique for training large language models. To address the throughput limitation of existing sequence-level
arXiv:2610.14427v1 Announce Type: cross Abstract: As watermarking of LLM-generated text enters deployment, users increasingly need to check text whose source is unknown. Existing detectors read the wa
arXiv:2610.14715v1 Announce Type: new Abstract: Early-stage design of heterogeneous UAV computing systems requires evaluating how algorithm, hardware, communication, and system topology affect closed-
arXiv:2610.15509v1 Announce Type: new Abstract: KV caches make long-context serving efficient by reusing past computation, but model switching breaks this reuse and forces the receiver to prefill the
arXiv:2610.18027v1 Announce Type: cross Abstract: Although machine learning potentials (MLPs) generalize across configurational and chemical compound spaces, their accuracy is commonly believed to be
arXiv:2610.17120v1 Announce Type: new Abstract: Recent frameworks in differential privacy (DP), such as privacy loss distributions and f-DP, provide lossless representations of the privacy leakage of
arXiv:2610.14226v1 Announce Type: new Abstract: Purpose : To develop and evaluate CAPTOR, a deep-learning vision-language foundation model for oncologic chest-abdomen-pelvis (CAP) CT interpretation. M
arXiv:2610.14957v1 Announce Type: new Abstract: Recent video generative models have shown strong capability in synthesizing high-quality and temporally coherent videos. Yet, adapting them for controll
arXiv:2602.23541v3 Announce Type: replace-cross Abstract: Previous work establishing completeness results for counterfactual identification has been circumscribed to the setting where the input data b
arXiv:2610.18026v1 Announce Type: new Abstract: Some observation-window-based KV cache compressors use prompt attention to identify important tokens but allocate uniform or predefined budgets across h
arXiv:2610.15321v1 Announce Type: new Abstract: Recent native 3D generators achieve high-quality asset creation by modeling structured 3D latents with flow-based transformers, but their high-resolutio
arXiv:2610.17926v1 Announce Type: new Abstract: Autoregressive video generation relies on memory retrieval to model long-range dependencies. This capability becomes particularly critical for multi-sho
arXiv:2610.15327v1 Announce Type: cross Abstract: Removing audio can shift a visual predictor's output without showing whether the task uses the intended audio information. We introduce Conditional In
arXiv:2610.14352v1 Announce Type: new Abstract: Signal Temporal Logic (STL) inference provides interpretable formulas for time series classification. For multiclass classification, however, accurate p
arXiv:2610.14395v1 Announce Type: new Abstract: Multimodal prediction models add a data source, such as imaging or an assay, to clinical information, and health systems must decide whether that added
arXiv:2610.18209v1 Announce Type: new Abstract: Cross-domain few-shot action recognition (CD-FSAR) aims to recognise unseen action classes in a target domain from a handful of labelled videos. Despite
arXiv:2610.16293v1 Announce Type: new Abstract: Garment manipulation requires inferring both garment identity and complete configuration from partial, self-occluded observations. This creates a chicke
arXiv:2610.15290v1 Announce Type: cross Abstract: We present Co-DSL, a framework in which users and LLMs co-design reusable spatial concepts for layout generation. In the first stage, our system allow
arXiv:2610.17733v1 Announce Type: new Abstract: Rubric-based reinforcement learning (RL) evaluates responses against explicit criteria to construct rewards, offering a viable way to train large langua
arXiv:2610.17224v1 Announce Type: new Abstract: The pass-all-test binary reward has become a standard recipe for training software engineering agents, but its sparsity eliminates difference of partial
arXiv:2610.15345v1 Announce Type: new Abstract: High-quality coding problems are expensive to collect. Benchmarks such as SWE-bench rely on substantial human curation, while synthetic alternatives typ
arXiv:2610.17282v1 Announce Type: cross Abstract: Standard diffusion processes with isotropic noise corruption are not spectrally neutral. They inherit a coarse-to-fine generation hierarchy from the n
arXiv:2610.17332v1 Announce Type: new Abstract: Vision large language models (VLLMs) are deployed in privacy-sensitive domains, raising training-data exposure concerns. Existing gray-box membership in
arXiv:2610.14237v1 Announce Type: new Abstract: Physically connected humanoids need consistent dynamics for internal actuator loops, inter-robot forces, and changing ground supports. We extend RoboCom
arXiv:2610.14514v1 Announce Type: new Abstract: Diffusion models pose significant risks regarding the generation of illicit content and copyright violations. This has catalyzed the development of mach
arXiv:2610.17221v1 Announce Type: new Abstract: Neural surrogates for Partial Differential Equations (PDEs) are usually trained on synthetic data from numerical simulators. As models grow and scaling
arXiv:2610.15146v1 Announce Type: new Abstract: Spiking neural networks target energy-efficient language modeling through sparse, binary activations, but the efficiency-accuracy tradeoff of spiking la
arXiv:2211.02478v4 Announce Type: replace-cross Abstract: In this article we prove that estimator stability, together with a gradient-growth condition on the expected fitted loss, is enough to provide
arXiv:2610.16993v1 Announce Type: new Abstract: A landmark result states that the expressive power of graph neural networks (GNNs) is bounded from above by the 1-dimensional Weisfeiler-Leman (1-WL) te
arXiv:2510.06640v3 Announce Type: replace-cross Abstract: State Space Models (SSMs) have emerged as efficient, linear-time alternatives to Transformer-Based Models (TBMs) for long-context processing.
arXiv:2610.14025v1 Announce Type: new Abstract: Activation steering controls large language model behavior by adding a direction to hidden activations during inference. For steering to work well, that
arXiv:2610.17098v1 Announce Type: new Abstract: The incorporation of footage from other sources has long been a concern from a copyright perspective, as such usage can harm the interests of rights hol
arXiv:2603.23356v2 Announce Type: replace-cross Abstract: We propose a novel clustering approach for point-cloud segmentation based on supervised contrastive metric learning (CML). Rather than predict
arXiv:2610.18434v1 Announce Type: cross Abstract: Expected improvement (EI) based on stochastic kriging (SK) surrogate is widely used in continuous simulation optimization, but unknown heteroscedastic
arXiv:2601.18313v2 Announce Type: replace-cross Abstract: This paper proposes a strictly convex chance-constrained stochastic control framework that accounts for uncertainty in control specifications
arXiv:2610.14341v1 Announce Type: new Abstract: We present CoPlanVLM, which uses a Vision Language Model (VLM) to translate a single natural-language instruction and image into coordinated paths for a
arXiv:2610.16737v1 Announce Type: cross Abstract: Video-to-robot pipelines for quadrupedal imitation insert a learned lifting stage, either a monocular depth model or a per-clip 3D reconstruction, to
arXiv:2610.18446v1 Announce Type: new Abstract: We present CoTL, a framework that learns a compact set of tokens that preserves scene geometry and appearance from unposed multi-view images. Our encode
arXiv:2610.17993v1 Announce Type: new Abstract: Certified machine unlearning ensures the proximity between the unlearned model and a model retrained without the data to be forgotten. Extending this fr
arXiv:2610.14953v1 Announce Type: new Abstract: Contrastive reinforcement learning (CRL) learns goal-conditioned values by associating state--action pairs with the states subsequently reached, assumin
arXiv:2610.16812v1 Announce Type: new Abstract: Symbolic regression (SR) aims to discover interpretable mathematical expressions from data and plays a key role in scientific discovery. However, existi
arXiv:2610.15391v1 Announce Type: new Abstract: Target-conditioned cyclic peptide design requires coordinating interfacial side chains with macrocyclic closure. Existing end-to-end generators concurre
arXiv:2610.14333v1 Announce Type: new Abstract: We study decentralized bandit learning in discounted infinite-horizon, general-sum Markov games with continuous actions. Agents observe the public state
arXiv:2512.14967v3 Announce Type: replace Abstract: We present a novel numerical method for solving McKean-Vlasov forward-backward stochastic differential equations (MV--FBSDEs) with common noise, com
arXiv:2610.15061v1 Announce Type: new Abstract: Accurate and efficient analysis of dental radiographs has become increasingly important for disease diagnosis and clinical decision making. In particula
arXiv:2610.16269v1 Announce Type: cross Abstract: In astrophysical complex TAIGA there are four Imaging Atmospheric Cherenkov telescopes (IACTs), located at a distance of 300-500 m from each other, du
arXiv:2610.16273v1 Announce Type: cross Abstract: Speech timing is fundamental for speech models to recognize words accurately, but how word-timing information is represented in speech models remains
arXiv:2610.16546v1 Announce Type: new Abstract: Basic probabilistic models form the basis of modern deep learning largely by defining the final activation layer of a network and allowing the networks
arXiv:2610.17316v1 Announce Type: cross Abstract: Deep unrolling methods for inverse problems augment traditional reconstruction algorithms with learned priors to improve their performance. These meth
arXiv:2610.14497v1 Announce Type: new Abstract: EEG foundation models (EFMs) have improved EEG representation learning by transferring knowledge from large-scale multi-subject pretraining to downstrea
arXiv:2610.14854v1 Announce Type: new Abstract: Contact-rich manipulation poses a stage-dependent sensory conflict: vision and proprioception are essential for localization and approach, when force is
arXiv:2610.14685v1 Announce Type: new Abstract: Recent advances in video diffusion enable novel-view video synthesis from a single input video, supporting world modeling, embodied intelligence, and ro
arXiv:2610.16570v1 Announce Type: new Abstract: Bronchoscopy inserts a camera through the airways to diagnose endoluminal disease. Locating the camera along the airway usually requires additional equi
arXiv:2610.14873v1 Announce Type: cross Abstract: Aspect Sentiment Quadruple Prediction (ASQP) is fundamentally a relational reasoning problem: identifying aspect-opinion-category-sentiment quadruples
arXiv:2610.16604v1 Announce Type: new Abstract: Humanoids increasingly demand lightweight leg mechanisms for agile, dynamic, and energy-efficient locomotion. Reducing distal inertia through proximal a