Knowledge catalogue
arXiv:2606.31004v1 Announce Type: new Abstract: AI-generated video detection benchmarks such as GenVidBench and AIGVDBench are the de facto leaderboards, yet most evaluation protocols leave uncontroll
arXiv:2606.31556v1 Announce Type: new Abstract: Generating high-quality novel views at real-time frame rates remains a central challenge in 3D vision, particularly in sparse-view scenarios. Neural rad
arXiv:2606.32018v1 Announce Type: new Abstract: Classifiers based on Deep Neural Networks exhibit strong performance across domains, yet can fail catastrophically if they rely on spurious correlations
arXiv:2410.11894v3 Announce Type: replace-cross Abstract: Dynamical systems form the foundation of scientific discovery, traditionally modeled with predefined state variables such as the angle and ang
arXiv:2606.31861v1 Announce Type: cross Abstract: Dynamic epistemic logic represents belief change via model transformations induced by epistemic events. Its standard formulation (Baltag, Moss, Soleck
arXiv:2606.30700v1 Announce Type: cross Abstract: Self-supervised learning enables audio representations that transfer across domains and tasks. We present BEST-RQ-2, an evolution of BEST-RQ that reta
arXiv:2606.31080v1 Announce Type: cross Abstract: Counterfactual explanation in abstract argumentation calls for an answer to the what-if query: would the topic argument still be accepted if the statu
arXiv:2606.31779v1 Announce Type: cross Abstract: Language models typically reason via explicit chain-of-thought (CoT), generating intermediate steps token-by-token. Latent CoT offers an alternative:
arXiv:2606.31326v1 Announce Type: new Abstract: Recently, unified image generation and understanding have been extensively explored. However, extending such unified modeling paradigms to the video dom
arXiv:2606.30919v1 Announce Type: cross Abstract: Edge-cloud inference collaborations are often designed with a routing estimator that decides whether to offload each frame from weak models at the edg
arXiv:2603.23867v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have been applied to a wide range of reasoning tasks, yet it remains unclear whether they can reason robustly un
arXiv:2510.17330v3 Announce Type: replace-cross Abstract: License plate image restoration is important not only as a preprocessing step for license plate recognition but also for enhancing evidential
arXiv:2602.08557v2 Announce Type: replace Abstract: Training non-prehensile manipulation policies in contact-rich settings is a core challenge in robotics. While Reinforcement Learning (RL) has demons
arXiv:2606.32012v1 Announce Type: cross Abstract: Uncertainty estimation has been a long-standing challenge in AI models; it amounts to 'knowing what you don't know,' and metacognition is notoriously
arXiv:2606.31497v1 Announce Type: new Abstract: Cloud-hosted foundation models enable robots to use semantic reasoning beyond onboard computational limits. In this setting, the robot executes a curren
arXiv:2606.30920v1 Announce Type: cross Abstract: We couple Forward Flux Sampling (FFS), a non-equilibrium rare-event technique from statistical mechanics, to a neural weather emulator (SDL-WXFormer,
arXiv:2507.14023v2 Announce Type: replace-cross Abstract: Regression problems with bounded continuous outcomes frequently arise in statistical and machine learning applications, such as the analysis o
arXiv:2606.31480v1 Announce Type: new Abstract: We study constrained online convex optimization with adversarial losses and stochastic or adversarial constraints. For stochastic constraints, existing
arXiv:2606.31819v1 Announce Type: new Abstract: This work introduces a new computational theory of mind grounded in set theory and hyperdimensional computing. Whereas traditional neural networks rely
arXiv:2606.30676v1 Announce Type: cross Abstract: Deploying spiking neural networks (SNNs) on neuromorphic hardware demands aggressive synaptic pruning while preserving temporal computation integrity.
arXiv:2606.30647v1 Announce Type: cross Abstract: Dense volumetric reconstruction of cloud microphysical fields from sparse ground-based instruments remains an open problem, largely because the availa
arXiv:2603.06136v2 Announce Type: replace Abstract: Diffusion distillation is central to accelerating image and video generation, yet existing methods are fundamentally limited by the denoising proces
arXiv:2606.31309v1 Announce Type: cross Abstract: While post-training backdoor detection and trigger inversion schemes have been developed for AIs used e.g. for images, there is a paucity of such meth
arXiv:2606.31557v1 Announce Type: cross Abstract: In the evolving threat landscape, adversaries exploit software vulnerabilities to launch sophisticated attacks, challenging traditional defenses. Alth
arXiv:2606.31232v1 Announce Type: new Abstract: Learning visual world models for planning requires compact latent dynamics that remain sensitive to actions, yet reconstruction-free joint-embedding obj
arXiv:2606.31956v1 Announce Type: cross Abstract: Much of written musical heritage is preserved and digitised at memory institutions: libraries, museums, and archives. Owing to their collection struct
arXiv:2603.23455v2 Announce Type: replace Abstract: Multi-Modal LLMs (MLLMs) demonstrate strong visual grounding capabilities on popular object detection benchmarks like OdinW-13 and RefCOCO. However,
arXiv:2606.31065v1 Announce Type: new Abstract: Reconstructing physics-based 3D assets -- geometry, materials, and illumination -- from multi-view images is a core problem in computer graphics and vis
arXiv:2604.14790v2 Announce Type: replace Abstract: Interactive Evolutionary Computation (IEC) provides a powerful framework for optimizing subjective criteria such as human preferences and aesthetics
arXiv:2606.30773v1 Announce Type: cross Abstract: We introduce a novel technique for scalable sampling of spin-system states with continuous symmetries using diffusion models. By applying our approach
arXiv:2606.31390v1 Announce Type: cross Abstract: Low-rank matrix optimization is often carried out via the Burer-Monteiro (BM) formulation, but choosing the factorization rank r is delicate and can s
arXiv:2512.21002v3 Announce Type: replace-cross Abstract: Distilling the capabilities from a large reasoning model (LRM) to a smaller student model often involves training on substantial amounts of re
arXiv:2606.31521v1 Announce Type: cross Abstract: Echo Planar Imaging (EPI) is the standard acquisition technique for diffusion and functional neuroimaging, enabling rapid imaging but suffering from g
arXiv:2606.31095v1 Announce Type: new Abstract: Reconstructing anatomically faithful vascular structures from clinically accessible imaging modalities is of substantial clinical significance. However,
DOGE showed they were morons with a series of gotcha moments: - DOGE claimed to have discovered USAID was paying for condoms for Gaza which they joked was for 'gay Hamas.' It turned out the condoms we
arXiv:2606.31373v1 Announce Type: new Abstract: Cycle self-training (CST) breaks the shared classifier assumption of the standard self-training framework, which is effective for unsupervised domain ad
Donald Trump made more than $2 billion last year while lying that affordability issues are a hoax and prices are going down. Never in American history has a man exploited the White House while in offi
arXiv:2606.31585v1 Announce Type: cross Abstract: The remarkable scalability of Transformers has expanded their application to 3D computer vision, where camera-aware positional encoding is crucial for
arXiv:2603.23297v2 Announce Type: replace Abstract: Despite their output being ultimately consumed by human viewers, 3D Gaussian Splatting (3DGS) methods often rely on ad-hoc combinations of pixel-lev
arXiv:2606.31063v1 Announce Type: cross Abstract: Gaussian process inference is often limited by cubic computational costs, a challenge that becomes more pronounced in spatio-temporal settings where p
arXiv:2606.30889v1 Announce Type: cross Abstract: Alternating recurrent events -- event-times of a specific nature that trigger a secondary refractory period -- occur in a wide-range of fields, includ
arXiv:2602.15008v2 Announce Type: replace Abstract: Diffusion models over discrete spaces have recently shown striking empirical success, yet their theoretical foundations remain incomplete. In this p
I can't verify the specific claims in this post title. The source appears to be a social media post attributed to Yann LeCun discussing Elon Musk's response to criticism regarding DOGE (Department of
ENPIRE -> ASPIRE, our 2nd work in the series for Physical AutoResearch. We are building the components for robot self-improvement, one /skill at a time. Today, we give robots a /skills library that se
arXiv:2603.21463v2 Announce Type: replace Abstract: The deep-learning based image matching networks can now handle significantly larger variations in viewpoints and illuminations while providing match
arXiv:2606.30999v1 Announce Type: new Abstract: In two-sided marketplaces with heterogeneous products, it is important to understand the causal relationship between additional supply and marketplace o
arXiv:2606.31760v1 Announce Type: new Abstract: Rolling-shutter cameras introduce characteristic distortions when imaging fast moving objects, and these effects are typically treated as artifacts to b
arXiv:2606.31331v1 Announce Type: new Abstract: Collaborative inference can improve predictive performance by integrating complementary information across agents, but applying collaborative fusion to
arXiv:2606.31110v1 Announce Type: new Abstract: Artificial neural networks (NNs) and machine learning (ML) algorithms are poorly understood from a theoretical perspective, which makes it difficult to
arXiv:2606.32040v1 Announce Type: new Abstract: Low-resolution face recognition (LR-FR) remains a challenging task due to poor feature extraction and aggregation, as probe images often contain limited
arXiv:2606.31742v1 Announce Type: cross Abstract: Explainable AI (XAI) methods have demonstrated significant success in recent years at identifying relevant features in input data that drive deep lear
arXiv:2509.12878v2 Announce Type: replace Abstract: Few-shot 3D point cloud semantic segmentation aims to segment novel categories using a minimal number of annotated support samples. However, prototy
arXiv:2606.31938v1 Announce Type: cross Abstract: Deploying Vision Transformer (ViT) models on edge platforms remains challenging due to their high computational demands and the architectural heteroge
arXiv:2606.31311v1 Announce Type: cross Abstract: Testing a new visual-analytics idea usually takes months: one needs to find a realistic data set, clean it, and implement an interactive prototype. We
arXiv:2606.30704v1 Announce Type: cross Abstract: Large language models (LLMs) excel across a wide range of tasks, yet their instance-specific solutions often lack the structural consistency needed fo
arXiv:2606.31136v1 Announce Type: new Abstract: Few-shot segmentation asks a model to delineate a target class in a query image from only a handful of annotated examples, a setting most acute in remot
arXiv:2606.31186v1 Announce Type: cross Abstract: Spontaneous speech is a vital non-invasive biomarker for Alzheimer's Disease (AD), yet many systems overlook non-linear structural disruptions and cli
arXiv:2601.21291v2 Announce Type: replace Abstract: Depth completion aims to predict a dense depth map from a color image with sparse depth measurements. Although deep learning methods have achieved s
arXiv:2606.30809v1 Announce Type: new Abstract: Existing 3D Gaussian Splatting (3DGS) systems distribute representation capacity uniformly across a scene, ignoring the fact that many downstream roboti
arXiv:2603.14965v2 Announce Type: replace Abstract: Novel view synthesis requires strong 3D geometric consistency and the ability to generate visually coherent images across diverse viewpoints. While