Knowledge catalogue
arXiv:2603.25418v2 Announce Type: replace Abstract: Teleoperation for contact-rich manipulation remains challenging, especially when using low-cost, motion-only interfaces that provide no haptic feedb
arXiv:2607.00382v1 Announce Type: new Abstract: We propose the first compression approach for image-to-shape Diffusion Transformers (DiTs) that substantially reduces model size while preserving geomet
arXiv:2607.00189v1 Announce Type: new Abstract: Camera pose estimation from image streams is a critical component of spatial world models that integrate perception into planning and decision-making. N
arXiv:2607.00325v1 Announce Type: cross Abstract: A growing body of literature suggests that training data membership inference problems are fundamentally hard tasks in modern language modeling settin
We don’t take stakes in healthy companies. Proposing that as last ditch regulatory capture attempt in commodity market is 😢 … or at best un-American disingenuous WWE politics, not pro-market, not pro-
🔥 We introduce LeVLJEPA: the first fully non-contrastive end-to-end vision-language pretraining method competitive with CLIP & SigLIP 💪🏼 👀 No negatives. No temperature. No momentum encoder. No teacher
arXiv:2607.00725v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) under a fixed reader-context budget forces a selection problem: of the evidence retrieved, only a fraction can be s
arXiv:2607.00365v1 Announce Type: cross Abstract: Artificial intelligence (AI) and quantum information (QI) are rapidly co-evolving. AI is becoming a practical tool for learning, designing, controllin
arXiv:2607.00394v1 Announce Type: cross Abstract: LLM agents increasingly rely on retrieval buffers to store and reuse past experience, yet the cache management policies governing these buffers remain
arXiv:2512.18934v2 Announce Type: replace-cross Abstract: Catastrophic forgetting poses a fundamental challenge in continual learning, particularly when models are quantized for deployment efficiency.
Something stinks in California’s climate policies. Years ago, the state set up a system that pays cattle farmers across the country to turn the methane emitted from cattle manure into natural gas, enc
arXiv:2607.01202v1 Announce Type: cross Abstract: We present World from Motion, a method for generating freely renderable dynamic 3D Gaussian representations from monocular videos. Our approach condit
arXiv:2408.16982v2 Announce Type: replace Abstract: 2D Gaussian Splatting has recently emerged as a significant method in 3D reconstruction, enabling novel view synthesis and geometry reconstruction s
arXiv:2606.31137v1 Announce Type: new Abstract: This paper proposes a Bayesian filtering-based approach for learning the dynamics of a physical system from partial, noisy measurements. We model the sy
arXiv:2606.30688v1 Announce Type: cross Abstract: Symmetry provides a quantum neural network structure, but on its own it does not keep the network trainable once noise is present. We ask which physic
arXiv:2511.22823v2 Announce Type: replace-cross Abstract: Weakly supervised learning has emerged as a practical alternative to fully supervised learning when complete and accurate labels are costly or
arXiv:2606.31323v1 Announce Type: new Abstract: Generating diverse, coherent, and plausible content from partially given inputs remains a fundamental challenge for diffusion models. Existing approache
arXiv:2606.31915v1 Announce Type: cross Abstract: While conformal prediction provides a general framework for uncertainty quantification in predictive inference, its application is often limited by co
arXiv:2606.31084v1 Announce Type: cross Abstract: Merge with Motion Vector Difference (MMVD) is a key coding tool in Versatile Video Coding for improving motion prediction accuracy. However, its exhau
arXiv:2606.32026v1 Announce Type: cross Abstract: Latent world models enable planning from high-dimensional observations by predicting future states in a compact latent space. However, these models ar
arXiv:2606.30652v1 Announce Type: cross Abstract: Transparency is increasingly mandated for public-sector AI systems, with organisations required to publish statements describing their AI use and over
arXiv:2606.30682v1 Announce Type: cross Abstract: Recent advances in language--audio retrieval have been largely driven by contrastive dual-encoder architectures that align audio and text in a shared
arXiv:2606.31991v1 Announce Type: cross Abstract: The tendency of large generative models to memorize training data makes sample verification critical for privacy auditing and copyright enforcement. C
arXiv:2606.30646v1 Announce Type: cross Abstract: Speech recruits the same executive, attentional, and working memory processes underlying instrumental activities of daily living, or IADLs, providing
arXiv:2606.31903v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) increasingly process long visual-token sequences, increasing the overall inference computation. Existing acce
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