Knowledge catalogue
arXiv:2609.05770v1 Announce Type: new Abstract: Differentially private (DP) fine-tuning methods treat sparse Mixture-of-Experts (MoE) models as a single dense block, ignoring that shared layers see al
arXiv:2609.07547v1 Announce Type: new Abstract: Multi-object tracking (MOT) has advanced rapidly in urban surveillance and autonomous driving, yet many trackers rely on ReID- and transformer-based app
arXiv:2606.06295v2 Announce Type: replace Abstract: Path sampling methods generate ensembles of reactive trajectories connecting metastable states, but extracting mechanistic insight from these data r
arXiv:2609.06581v1 Announce Type: new Abstract: Small-object detection remains challenging because limited pixels cause information loss and suppress the scale knowledge encoded in pretrained detector
arXiv:2609.06382v1 Announce Type: cross Abstract: In many scientific disciplines, weak signals of interest are obscured by dominant nuisance signals that are several orders of magnitude stronger. Reco
arXiv:2609.06221v1 Announce Type: new Abstract: Vision-language-action (VLA) models have substantially advanced language-guided robot manipulation, yet reliable execution still hinges on identifying w
arXiv:2609.07206v1 Announce Type: new Abstract: Trajectory representation learning underpins a wide range of trajectory analytics tasks; however, most existing self-supervised approaches, whether disc
arXiv:2609.08365v1 Announce Type: new Abstract: Text-to-motion (T2M) generation maps natural language to human joint movements, aiding gaming, VR, and robotics. Retrieval-Augmented Text-to-Motion (RAG
arXiv:2508.11431v3 Announce Type: replace Abstract: An object can disappear from a 3D scene, yet still be detectable. Even after visual removal, modern vision models may infer what was originally pres
arXiv:2609.05438v1 Announce Type: cross Abstract: The human brain folds in utero, primarily during late gestation. Shortly after birth, cortical folding patterns are established and remain stable ther
arXiv:2609.06154v1 Announce Type: new Abstract: One-shot federated graph learning generally aims to train Graph Neural Networks (GNNs) across clients with disconnected subgraphs in a single communicat
arXiv:2607.10147v2 Announce Type: replace Abstract: Automated chest X-ray report generation has recently benefited from reinforcement learning (RL) and large language models. However, RL training ofte
arXiv:2609.08064v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in settings where rare but severe harmful generations can have significant consequences. Existing
arXiv:2609.07096v1 Announce Type: new Abstract: Humanoid locomotion requires control policies that remain stable under imperfect sensing while exploiting temporal context for consistent motion. We pre
arXiv:2609.06346v1 Announce Type: new Abstract: Continual learning (CL) enables models to acquire new knowledge from sequentially arriving tasks while retaining previously learned knowledge. However,
arXiv:2410.09563v2 Announce Type: replace Abstract: In the domain of computer vision, optical flow stands as a cornerstone for unraveling dynamic visual scenes. However, the challenge of accurately es
arXiv:2602.09740v3 Announce Type: replace Abstract: Connected and Autonomous Vehicles (CAVs), which is critical for achieving Level-5 autonomous driving. Safe and reliable CAV navigation depends on ro
arXiv:2501.10621v2 Announce Type: replace-cross Abstract: Driven by the need to address labor shortages and meet the demands of a rapidly growing population, robotic automation has become a critical c
arXiv:2602.01533v2 Announce Type: replace Abstract: Online handwritten character recognition leverages stroke order and dynamic features, which generally provide higher accuracy and robustness compare
arXiv:2603.06356v2 Announce Type: replace Abstract: Cooperative transport and manipulation of heavy or bulky payloads by multiple manipulators requires coordinated formation tracking, while simultaneo
arXiv:2609.05850v1 Announce Type: new Abstract: Despite the significant efforts devoted to aligning large language models (LLMs) with human values and ensuring safe deployment, recent work has reveale
arXiv:2609.06385v1 Announce Type: new Abstract: Pretrained 3D generative models produce detailed geometry and appearance but are primarily designed for object-centric generation within a limited spati
arXiv:2609.05826v1 Announce Type: new Abstract: Dynamic programming for optimal classification trees becomes computationally expensive as the numbers of features and training samples increase. We deve
arXiv:2609.05594v1 Announce Type: new Abstract: Diverse and simulation-ready indoor scenes are essential for interactive entertainment and embodied AI, yet their scalable generation remains challengin
arXiv:2609.06257v1 Announce Type: new Abstract: Reliable marine-engine fault diagnosis in maritime IoT is challenged by distributed data ownership, heterogeneous fault distributions, and continuously
arXiv:2609.08346v1 Announce Type: new Abstract: Moving-object perception must decide which image regions correspond to real motion and keep every instance identified over time. Methods that read motio
arXiv:2609.07982v1 Announce Type: new Abstract: Standard semi-supervised learning (SSL) typically relies on labelled and unlabelled data sharing a common marginal distribution. This assumption is ofte
arXiv:2609.06547v1 Announce Type: new Abstract: Real-time 3D mapping is fundamental for autonomous robotic navigation, with Euclidean Signed Distance Fields (ESDFs) serving as the standard representat
arXiv:2609.06718v1 Announce Type: new Abstract: Humanoid soccer is a challenging testbed for dynamic whole-body control, requiring robots to coordinate balance, locomotion, object interaction, and ski
arXiv:2609.06906v1 Announce Type: cross Abstract: We develop a new low-accuracy sampler, called smoothed Picard Hamiltonian Monte Carlo, which combines Gaussian smoothing, Picard iteration, and higher
arXiv:2609.07608v1 Announce Type: new Abstract: Bridging the simulation-to-reality gap in roadside LiDAR requires addressing several coupled discrepancies, including scene geometry, sampling density,
arXiv:2609.06186v1 Announce Type: new Abstract: Prioritized Sweeping (PS) accelerates model-based reinforcement learning by selecting backups according to Bellman residual magnitude. In nonstationary
arXiv:2609.08219v1 Announce Type: cross Abstract: Neural networks acquire internal representations through learning. In this work, we formulate stochastic gradient descent (SGD) as a Markovian stochas
arXiv:2609.07571v1 Announce Type: new Abstract: 360{eg} salient object detection (SOD) aims to accurately segment salient regions across a full field of view. However, equirectangular projection (ERP)
arXiv:2609.09012v1 Announce Type: new Abstract: Spherical observations provide global visual context for 3D scene understanding. However, visual information is encoded in an angular domain, whereas th
arXiv:2510.08999v2 Announce Type: replace Abstract: Compressing large-scale neural networks is essential for deploying models on resource-constrained devices. Most existing methods adopt weight prunin
arXiv:2507.18073v2 Announce Type: replace Abstract: Deploying large language models (LLMs) is challenging due to their massive parameters and high computational costs. Ultra low-bit quantization can s
arXiv:2609.07148v1 Announce Type: cross Abstract: While Reinforcement Learning (RL) effectively incentivizes reasoning in Large Language Models, current pipelines are hindered by training instability
arXiv:2609.05916v1 Announce Type: new Abstract: Large vision-language models (LVLMs) achieve strong multimodal understanding, but the hundreds to thousands of visual tokens they process impose substan
arXiv:2609.06289v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in alignment-sensitive contexts, activation steering has emerged as a lightweight, inference
arXiv:2609.06473v1 Announce Type: new Abstract: Inference-time activation steering enables behavioral control of large language models without parameter modification, while post-training quantization
arXiv:2609.08543v1 Announce Type: new Abstract: Despite recent advances in surgical vision-language models (VLMs), temporal reasoning remains limited because existing supervision is largely frame-cent
arXiv:2609.06929v1 Announce Type: new Abstract: Inter-frame affine misalignment caused by platform jitter and attitude adjustments poses a fundamental challenge for multi-frame analysis of point targe
arXiv:2609.05550v1 Announce Type: new Abstract: Near-infrared (NIR) video is a promising modality for contactless sleep monitoring, but recent video-based sleep staging methods often use it as a route
arXiv:2603.28678v2 Announce Type: replace Abstract: We introduce PACE, a backpropagation-free continual test-time adaptation system that directly optimizes the affine parameters of normalization layer
arXiv:2609.08642v1 Announce Type: new Abstract: Exploration in reinforcement learning (RL) remains a fundamental challenge. Recent goal-conditioned RL strategies (which select goals to encourage broad
arXiv:2609.08317v1 Announce Type: new Abstract: Objective assessment of Freezing of Gait (FoG) in Parkinson's disease (PD) relies predominantly on wearable Inertial Measurement Units (IMUs). While IMU
arXiv:2601.13713v2 Announce Type: replace-cross Abstract: Software testing is crucial for ensuring the correctness and reliability of software systems. Automated generation of issue reproduction tests
arXiv:2510.19251v2 Announce Type: replace-cross Abstract: Predicting which hypothetical inorganic crystals can be experimentally realized remains a central challenge in accelerating materials discover
arXiv:2609.07441v1 Announce Type: new Abstract: Biomedical tables often combine thousands of measured variables with only tens or hundreds of labelled samples, a regime that is poorly represented in g
arXiv:2609.09158v1 Announce Type: new Abstract: We study the problem of navigating cluttered indoor environments with a humanoid robot. Unlike conventional methods that model navigation as a 2D path p
arXiv:2609.07540v1 Announce Type: new Abstract: Contrastive learning approaches achieve strong performance by training models to bring similar samples closer while pushing dissimilar samples apart. A
arXiv:2609.07461v1 Announce Type: new Abstract: We consider reinforcement learning in environments with dynamics that undergo an irreversible phase transition governed by a hidden temporal pattern. Th
arXiv:2609.07184v1 Announce Type: cross Abstract: We present tensor network representations for discrete maximum entropy distributions under expectation constraints. To this end, we introduce Computat
arXiv:2609.08901v1 Announce Type: new Abstract: Approximate machine unlearning aims to remove the influence of specific training data from a trained model without retraining from scratch. We identify
Gary Marcus argues that current generative‑AI models fail to meet basic standards of reliability because they routinely hallucinate facts, amplify existing biases, and provide no transparent audit tra
arXiv:2609.07843v1 Announce Type: cross Abstract: Machine learning has shown its largest gains in the band below 10 ms inside a 3GPP new radio (NR) 5G distributed unit (DU): link adaptation, per-slot
arXiv:2609.07216v1 Announce Type: new Abstract: The rapid evolution of video generation has shifted the paradigm from pure text-driven to multi-conditional controllable generation, with reference imag
arXiv:2603.25579v2 Announce Type: replace-cross Abstract: A key capability of modern neural networks is their capacity to simultaneously learn underlying rules and memorize specific facts or exception
arXiv:2505.04376v2 Announce Type: replace-cross Abstract: LiDAR-based perception plays a fundamental role in modern robotic systems for environment understanding and navigation. Single-photon LiDAR (S