Knowledge catalogue
arXiv:2610.05699v1 Announce Type: new Abstract: The efficacy of traditional disease prediction is limited by spatial gaps and temporal lags, which impact the timing and targets of resource deployments
arXiv:2604.01142v2 Announce Type: replace-cross Abstract: Reinforcement learning has shown strong performance in robotic manipulation, but learned policies often degrade in performance when test condi
arXiv:2601.22891v3 Announce Type: replace Abstract: Linear temporal logic (LTL) has emerged as a powerful formalism for specifying structured, temporally extended tasks in multi-task reinforcement lea
arXiv:2610.06825v1 Announce Type: cross Abstract: Scientific figures often encode quantitative results that are not readily available in machine-readable form, making accurate plot digitization import
arXiv:2610.05570v1 Announce Type: new Abstract: Existing thermodynamically consistent neural operators impose the GENERIC degeneracy conditions by projecting the reversible operator onto the complemen
arXiv:2610.04638v1 Announce Type: new Abstract: Actor-critic methods reuse past experience to improve sample efficiency. However, historical data are typically regarded as off-policy samples for the c
arXiv:2610.06032v1 Announce Type: cross Abstract: Physics simulators can support the discovery of quantum experiments by predicting the states generated by experimental configurations. When these simu
arXiv:2610.05476v1 Announce Type: new Abstract: Scaling decentralized learning changes not only the number of clients N, but also the dynamics of information propagation and consensus. We argue that t
arXiv:2610.05010v1 Announce Type: new Abstract: Portrait aesthetic assessment assigns comparable scores according to how effectively human-centered images fulfill their photographic intent. These scor
arXiv:2610.04916v1 Announce Type: new Abstract: Urban navigation requires embodied agents to pursue long-horizon goals through local decisions based on egocentric observations. However, existing agent
arXiv:2610.04976v1 Announce Type: new Abstract: We evaluate language models' capability to generate novel research ideas through the lens of compression. We aim to lower-bound the potentially tiny pro
arXiv:2610.04162v1 Announce Type: new Abstract: Selecting the best k items out of m candidates is a critical component of modern large language model systems, such as document selection in Retrieval-A
arXiv:2610.05416v1 Announce Type: new Abstract: Natively training joint video-audio generation models at higher resolutions empowers them to learn richer visual details and sharper motion dynamics. Ho
arXiv:2610.05102v1 Announce Type: new Abstract: We study differentially private learning problems in the realizable setting, where a hypothesis is specified by k components. A direct iteration of priv
arXiv:2610.06822v1 Announce Type: new Abstract: We study mistake bounds for differentially private online learning and online prediction under oblivious realisable adversaries. Online learning require
arXiv:2610.03972v1 Announce Type: new Abstract: Ising machines have emerged as promising hardware accelerators for intractable optimization and sampling problems, yet their practical impact increasing
arXiv:2610.04736v1 Announce Type: new Abstract: A pedestrian with a phone could be shown where nearby people will be in the next few seconds, if the forecast stays on the ground while the phone moves,
arXiv:2610.03846v1 Announce Type: cross Abstract: Probability-flow ordinary differential equations (PF-ODEs) are widely used as deterministic samplers for score-based diffusion models. Their usual jus
arXiv:2603.17850v2 Announce Type: replace Abstract: Recent Vision-Language-Action (VLA) models equipped with Flow Matching (FM) action heads achieve state-of-the-art performance in complex robot manip
arXiv:2511.05420v3 Announce Type: replace Abstract: Data-driven fault diagnosis models for smart grids are usually trained once on a fixed dataset, whereas in operation new fault types appear and moni
arXiv:2603.22118v2 Announce Type: replace Abstract: We use fused deposition modeling (FDM) 3D printing as a case study of how manufacturing robots can use imperfect AI. In FDM, print configuration str
arXiv:2610.04100v1 Announce Type: new Abstract: Model compression strategies are widely employed to reduce memory footprint and network complexity, particularly for devices with constrained computatio
arXiv:2610.05918v1 Announce Type: new Abstract: Existing data-driven infrared small target detection (ISTD) methods typically require large-scale datasets with accurate pixel-level annotations for mod
arXiv:2610.04928v1 Announce Type: new Abstract: This paper studies GRPO at 1B scale from both directions: what estimator choices do to the learning signal, and what a degraded reward signal does to wh
arXiv:2610.06103v1 Announce Type: new Abstract: Risk-aware planners score paths on uncertain elevation maps using the path cost's mean and standard deviation. Modeling rigid contact, however, requires
arXiv:2610.04038v1 Announce Type: new Abstract: Synthetic data are increasingly used as an alternative to sharing sensitive records. However, synthetic data generation does not guarantee privacy, as d
arXiv:2610.05807v1 Announce Type: cross Abstract: Protocol choices can change the conclusions drawn from log anomaly detection benchmarks even when detector settings are fixed. We present a joint empi
arXiv:2610.04519v1 Announce Type: new Abstract: Estimating treatment effects from observational data typically relies on the No Unmeasured Confounding Assumption (NUCA), which rarely holds in practice
arXiv:2610.03894v1 Announce Type: cross Abstract: A deployed LLM agent emits tool calls, queries, and code that can be silently wrong -- by the time the error surfaces, the action has run. Frontier ch
arXiv:2610.04920v1 Announce Type: new Abstract: Pretrained world models can generate diverse environments, yet users often want to explore a particular scene specified by their own video. This require
arXiv:2610.04737v1 Announce Type: cross Abstract: Reasoning models can remain capable of solving a task while still defaulting to cheaper but misleading shortcuts. This creates a central oversight pro
arXiv:2610.05240v1 Announce Type: new Abstract: Time-series foundation models offer a unified approach to forecasting across heterogeneous domains. Textual context and auxiliary observations provide c
arXiv:2610.06404v1 Announce Type: new Abstract: We consider the stability of multi-step reasoning processes, which have extensive applications in language models, including chain-of-thought and algori
arXiv:2610.06076v1 Announce Type: cross Abstract: Preparing quantum states from classical data can cost more than the computation they serve; most loaders tailor a circuit to each input. Here we show
arXiv:2511.01467v4 Announce Type: replace-cross Abstract: We study quantum differential privacy (QDP) by defining a notion of the order of informativeness between two pairs of quantum states. In parti
arXiv:2610.04543v1 Announce Type: cross Abstract: Quantum key distribution proves its protocol secure and says nothing about the hardware beneath it, so military and government operators fielding it f
arXiv:2610.04299v1 Announce Type: new Abstract: Self-evolving reasoning models learn from their own generated questions, yet repeated self-training can lead to performance collapse. In this paper, we
arXiv:2610.04913v1 Announce Type: new Abstract: World Action Models (WAMs) emerge as a promising foundation for policy refinement by predicting the consequences of sampled actions. However, visually p
arXiv:2603.05925v2 Announce Type: replace Abstract: In this paper, we propose a Rectified Flow Auto Coder (RAC) inspired by Rectified Flow to replace the traditional VAE: 1. It achieves multi-step dec
arXiv:2610.06121v1 Announce Type: new Abstract: Adverse weather and poor illumination remain major challenges for robust ego-trajectory planning in mobile autonomy. 4D radar offers reliable sensing un
arXiv:2610.04438v1 Announce Type: cross Abstract: We present RAGrasp, a retrieval-augmented pipeline for planar parallel-jaw grasping from a compact set of locally collected, grasp-annotated RGB-D (co
arXiv:2610.06401v1 Announce Type: cross Abstract: Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external content. Existing training-ti
arXiv:2610.06266v1 Announce Type: new Abstract: Freeway on-ramp merges are major sources of congestion, causing significant economic and environmental costs. While Deep Reinforcement Learning (DRL) of
arXiv:2610.05220v1 Announce Type: new Abstract: Carousel interfaces allow a recommender system to directly observe how far a user has browsed. This signal distinguishes displayed but unclicked items f
arXiv:2610.05969v1 Announce Type: new Abstract: Diffusion policies provide expressive action distributions for continuous-control reinforcement learning. However, safety-aware online diffusion policy
arXiv:2610.04406v1 Announce Type: new Abstract: Safe robot control often requires combining long-horizon performance optimization with hard state and input constraints, but existing approaches tend to
arXiv:2610.03888v1 Announce Type: cross Abstract: Reconstructing global sea surface pH from sparse observations is critical for monitoring ocean acidification and understanding marine carbon cycling.
arXiv:2610.06703v1 Announce Type: cross Abstract: Background music that matches the mood of a text has been shown to make readers feel more immersed and improve their reading experience, motivating re
arXiv:2610.06324v1 Announce Type: new Abstract: CLIP-like vision-language models remain a cornerstone of multimodal systems, yet their scores stay near chance on directed spatial relations, such as wh
arXiv:2610.04266v1 Announce Type: new Abstract: This paper presents a conformal-seeded hybrid strategy for solving inverse kinematics of offset, redundant 7-DoF robot arms of the humanoid class. Analy
arXiv:2610.06617v1 Announce Type: new Abstract: World Action Models (WAMs) incorporate visual representations from video generation backbones to guide action prediction. Recent efficient WAMs adopt Mi
arXiv:2607.09082v2 Announce Type: replace Abstract: Training-free in-context segmentation enables new object categories to be introduced at inference time from a single annotated reference image, elim
arXiv:2610.06010v1 Announce Type: new Abstract: Ultrasound visual servoing is essential for autonomous robotic ultrasound, yet 6-DoF probe control from 2D B-mode images remains challenging due to limi
arXiv:2610.05185v1 Announce Type: new Abstract: GUI grounding is a critical capability for GUI agents powered by vision-language models, helping them execute user instructions by locating the correspo
arXiv:2610.05151v1 Announce Type: new Abstract: Visuomotor policies can execute familiar tasks yet lack the corrective behavior needed after their own mistakes. We present a framework for recursive se
arXiv:2610.06843v1 Announce Type: new Abstract: LLM agents that orchestrate frozen vision-language-action (VLA) policies improve across episodes through text memory, which records what the agent did b
arXiv:2610.05074v1 Announce Type: new Abstract: Low-light UAV-based RGB-infrared oriented small-vehicle detection is important for nighttime traffic monitoring, emergency response, and urban inspectio
arXiv:2610.03997v1 Announce Type: new Abstract: Robots can acquire bad habits from a few defective moments in otherwise useful teleoperation. In mixed-quality robot data, normal and problematic demons
arXiv:2510.16444v2 Announce Type: replace Abstract: Who is being described, where are they, and what are they doing? Referring Atomic Video Action Recognition (RAVAR) answers these questions jointly b
arXiv:2610.04185v1 Announce Type: new Abstract: Referring multi-object tracking (RMOT) takes a video and a language expression as input and tracks all referred objects. Many tracking requirements invo