Knowledge catalogue
arXiv:2609.32163v1 Announce Type: new Abstract: Temporal context is essential for camera-only multi-view 3D object detection. Existing streaming detectors maintain and propagate query states from one
arXiv:2609.34470v1 Announce Type: new Abstract: We present EditWorld, a video world model for precise editing and flexible referencing in interactable worlds. Existing video world models primarily foc
arXiv:2609.32908v1 Announce Type: new Abstract: Neural theorem provers must both propose tactics and decide which valid successor states to explore. We study whether one-step Lean transitions provide
arXiv:2609.32652v1 Announce Type: cross Abstract: We study when geometry-induced soft state abstractions admit accurate finite-dimensional linear dynamics. Each state is represented by simplex-valued
arXiv:2609.33928v1 Announce Type: new Abstract: Predicting spatial gene expression from histology images could scale spatial transcriptomics (ST) to image-only cohorts, but conventional histology-base
arXiv:2609.33591v1 Announce Type: new Abstract: Low-precision Transformer systems increasingly quantize attention matrix multiplications, while softmax often remains at higher precision. During pretra
arXiv:2609.33513v1 Announce Type: new Abstract: Adversarial patches for aerial perception are typically evaluated as digital composites, with printing left as an implementation detail. This study impo
arXiv:2609.32354v1 Announce Type: new Abstract: This abstract addresses the incorporation of human motion prediction into proactive and dynamic human-aware motion planning, with the goal of enabling s
arXiv:2609.34613v1 Announce Type: cross Abstract: Flow matching (FM) has recently emerged as a promising framework for generative modeling due to its conceptual simplicity and strong empirical perform
arXiv:2609.32711v1 Announce Type: new Abstract: We present ProDyGS, a novel dynamic 3D Gaussian Splatting framework for high-quality novel view synthesis from videos captured by a single static camera
arXiv:2609.32811v1 Announce Type: new Abstract: Accident anticipation aims to recognize anomalous driving cues before a crash while avoiding false alarms during normal driving. Existing approaches typ
arXiv:2609.33701v1 Announce Type: new Abstract: Pretrained biomedical vision-language models achieve strong zero-shot performance in biomedical image classification. However, downstream biomedical cla
arXiv:2609.31862v1 Announce Type: cross Abstract: Reconstruction and simulation at a collider experiment are long chains of specialised algorithms, each tuned to a single step. We explore how one mode
arXiv:2609.35080v1 Announce Type: new Abstract: We study post-hoc refinement of frozen node classifiers: given only the graph G and class distributions Q predicted by a frozen model, can we improve ac
arXiv:2604.02102v2 Announce Type: replace-cross Abstract: Speech representations from self-supervised speech models (S3Ms) are known to be sensitive to phonemic contrasts, but their sensitivity to pro
arXiv:2609.33461v1 Announce Type: cross Abstract: Runtime monitoring traditionally evaluates a specification that is fixed before execution or externally modified when requirements change. In learning
arXiv:2609.35174v1 Announce Type: new Abstract: We propose a lifted reformulation of supervised classification that improves the final accuracy of standard classifiers without changing the architectur
arXiv:2609.35023v1 Announce Type: new Abstract: Lightweight scene proxies let creators control scene layout and motion while leaving room for imagination in appearance, lighting, and visual effects. H
arXiv:2609.33501v1 Announce Type: new Abstract: Photoplethysmography (PPG) has become an important modality for continuous cardiovascular monitoring, including atrial fibrillation (AF) detection. Howe
arXiv:2509.22161v4 Announce Type: replace Abstract: Vector quantization, which discretizes a continuous vector space into a finite set of representative vectors (a codebook), has been widely adopted i
arXiv:2609.33088v1 Announce Type: new Abstract: Traditional change detection (CD) identifies changes between bi-temporal remote sensing images, while semantic change detection (SCD) assigns predefined
arXiv:2609.32455v1 Announce Type: new Abstract: Camera pose estimation from multi-view images remains a challenge in computer vision. Traditional methods often address this problem using Structure-fro
arXiv:2609.34718v1 Announce Type: new Abstract: Reinforcement learning (RL) changes not only what language models say, but also how much they say, often increasing response length at the cost of token
arXiv:2609.33923v1 Announce Type: cross Abstract: A single random Gaussian probe gives an unbiased estimate of the squared Frobenius norm of a layer's quantization error. The estimator is well-behaved
arXiv:2609.34273v1 Announce Type: cross Abstract: The projection of queries and keys are central to the attention mechanism in Transformer architectures. While they are mathematically symmetric, they
arXiv:2510.13854v2 Announce Type: replace-cross Abstract: We introduce Rule-to-Tag (R2T), a framework that turns linguistic rules into the training signal for neural sequence taggers in low-resource l
arXiv:2609.33674v1 Announce Type: new Abstract: Graph neural networks (GNNs) are often called long-range because their architecture can connect distant nodes, but this does not show whether they use d
arXiv:2609.32595v1 Announce Type: new Abstract: Safe and robust robot navigation across diverse environments requires a high-level understanding of complex scenes and the ability to carry it into stab
arXiv:2609.34032v1 Announce Type: new Abstract: A manga reader meets a character on one page and knows them on sight a hundred pages later, without ever being handed a cast list. Re-identifying comic
arXiv:2609.33420v1 Announce Type: cross Abstract: Recovering probability measures from their moments has numerous applications, esp. in connection with the method of moments in statistics and optimiza
arXiv:2609.34257v1 Announce Type: cross Abstract: Repeatedly training language models on their own generated data may create a synthetic-data feedback loop in which errors and distributional biases ar
arXiv:2609.33854v1 Announce Type: new Abstract: Driving policies require capabilities of scene understanding and future evolution prediction. To achieve this goal, current end-to-end models typically
arXiv:2609.35405v1 Announce Type: new Abstract: Pretrained 2D foundation models offer a practical alternative to dedicated 3D pretraining for brain structural magnetic resonance imaging (sMRI), but th
arXiv:2609.34904v1 Announce Type: new Abstract: Graph neural networks (GNNs) need to exploit improved message passing without surrendering control over predictions already trusted in deployment. We in
arXiv:2609.32669v1 Announce Type: cross Abstract: Attention weights depend on token counts, which change with the representation of a signal. We study refinement symmetry: splitting a representation w
arXiv:2609.32068v1 Announce Type: new Abstract: Motion retargeting transfers motion across characters with different skeletal structures while preserving semantic intent and physical plausibility. Des
arXiv:2609.32716v1 Announce Type: new Abstract: Superpixel copula models provide stable regional evidence for heterogeneous remote sensing change detection, but a single label per region limits locali
arXiv:2609.34587v1 Announce Type: new Abstract: Reinforcement learning is increasingly used to post-train vision-language models for image-to-code generation, such as generating SVG code from a refere
arXiv:2609.33016v1 Announce Type: new Abstract: Large Language Model (LLM) pretraining performance is jointly shaped by three components of the training triplet: the optimizer, model architecture, and
arXiv:2609.34163v1 Announce Type: new Abstract: Vision-language navigation (VLN) is typically evaluated as a one-way task, although deployed robots may need to return after reaching a goal. We study c
arXiv:2609.35612v1 Announce Type: new Abstract: Remote sensing novel view synthesis under sparse observations remains challenging due to insufficient geometric constraints and limited cross-view super
arXiv:2609.31694v1 Announce Type: new Abstract: Removing an invisible watermark and concealing the forensic evidence are distinct objectives: successfully disrupting the embedded watermark does not im
arXiv:2609.35264v1 Announce Type: new Abstract: Camera-LiDAR detectors can continue to consume unreliable features even when both sensors remain present, synchronized, and calibrated. We introduce Bou
arXiv:2609.31630v1 Announce Type: new Abstract: Replay-based continual learning almost always consolidates in a dedicated offline phase or by interleaving replayed samples with the input stream, where
arXiv:2609.33892v1 Announce Type: new Abstract: This paper proposes a residual learning-based control framework for heterogeneous vehicle platoons subject to parametric uncertainty and external distur
arXiv:2609.33895v1 Announce Type: new Abstract: In diffusion-based generation, a neural network can be trained to predict the clean data, the noise, or the velocity from a noisy input. These predictio
arXiv:2609.34942v1 Announce Type: new Abstract: The inference efficiency of Multimodal Large Language Models (MLLMs) is severely constrained by massive visual token sequences induced by high-resolutio
arXiv:2609.33412v1 Announce Type: new Abstract: Despite rapid progress in vision-language-action (VLA) models, existing reasoning paradigms still face a fundamental state-representation mismatch in op
arXiv:2609.35593v1 Announce Type: new Abstract: 3D vision transformers such as VGGT predict camera poses and scene geometry from multi-view images in a single forward pass, but their global attention
arXiv:2609.33851v1 Announce Type: new Abstract: Contextualization, the core operation of language modeling, transmits information across words to build sentence-specific word representations. Prior wo
arXiv:2609.32899v1 Announce Type: new Abstract: Hyperbolic space can embed intrinsic hierarchies in data with low distortion due to the exponential growth of volume with distance from the origin. Howe
arXiv:2609.35394v1 Announce Type: new Abstract: Video Large Language Models (Video LLMs) have achieved remarkable progress in video understanding, but their inference efficiency is constrained by the
arXiv:2609.34566v1 Announce Type: new Abstract: Predicting observed dynamics does not establish recovery of the underlying physical mechanism. Can machine learning retrace the hidden-state reasoning b
arXiv:2609.35086v1 Announce Type: new Abstract: In this work, we study portfolio optimization under the stochastic discount factor (SDF) framework by learning market state representations that capture
arXiv:2609.32984v1 Announce Type: new Abstract: Recursive self-improvement (RSI) offers a promising path for overcoming the limited visual capability of current medical imaging agents. Yet applying RS
arXiv:2609.32729v1 Announce Type: cross Abstract: AdaGrad and AdaGrad-Norm are widely used adaptive methods, but their precise behavior in stochastic convex optimization remains less understood. We fi
arXiv:2609.33716v1 Announce Type: new Abstract: Diffusion-based unsupervised domain adaptation (UDA) improves cross-domain transfer by generating target-specific synthetic data for downstream adaptati
arXiv:2609.35441v1 Announce Type: new Abstract: State space models (SSMs) achieve efficient sequence processing because their affine state updates are closed under composition and can therefore be eva
arXiv:2609.35623v1 Announce Type: cross Abstract: Scaffold hopping is a critical task in drug discovery, which seeks to discover new, structurally distinct molecules that share key functional groups a
arXiv:2609.35311v1 Announce Type: new Abstract: Action-conditioned video world models predict future robot interactions from multiple cameras, yet their outputs remain disparate video collections rath