Knowledge catalogue
arXiv:2606.03831v1 Announce Type: new Abstract: This paper investigates non-stationary online learning using the metric of interval regret, which requires an online algorithm to perform well over ever
arXiv:2606.03264v1 Announce Type: new Abstract: We introduce PaddleOCR-VL-1.6, an upgraded compact document parsing model built upon PaddleOCR-VL-1.5. Although PaddleOCR-VL-1.5 establishes a strong 0.
arXiv:2606.03479v1 Announce Type: new Abstract: Dynamic 3D Gaussian Splatting (3DGS) methods reconstruct time-varying scenes from synchronized multi-camera video using photometric supervision. When a
arXiv:2606.02919v1 Announce Type: new Abstract: We present a diffusion-based method for relighting dynamic portrait videos with photorealism and temporal consistency. Our method is fueled by a hybrid
arXiv:2606.03989v1 Announce Type: new Abstract: Images composed of 2D pixel arrays are the standard input to computer vision algorithms, yet many underlying computations can be distributed across pixe
arXiv:2606.03943v1 Announce Type: new Abstract: Video-Action Models (VAMs) leverage the broad visual dynamics captured by pre-trained video diffusion models, offering a promising path toward generaliz
arXiv:2606.02632v1 Announce Type: cross Abstract: Modern Machine Learning (ML) and Artificial Intelligence (AI) models, especially large language models (LLMs), are increasingly used to generate scien
arXiv:2606.02981v1 Announce Type: new Abstract: Best-of-N inference scaling (drawing N candidate answers from a language model and returning the one a reward model ranks highest) improves accuracy by
arXiv:2606.03444v1 Announce Type: cross Abstract: Unifying the complementary strengths of diverse Vision Foundation Models (VFMs) into a single efficient model is highly desirable but challenged by th
arXiv:2606.03257v1 Announce Type: cross Abstract: Spiking Vision Transformer (SViT) models are promising low-power ViT models for solving vision-based tasks with state-of-the-art performance. However,
arXiv:2504.01250v2 Announce Type: replace Abstract: This paper presents the Robust Recurrent Deep Network (R2DN), a scalable parameterization of robust recurrent neural networks for machine learning a
arXiv:2601.20844v3 Announce Type: replace-cross Abstract: This paper studies the Minimal Embeddable Dimension (MED): the least dimension in which there exists a configuration of m object vectors so th
arXiv:2505.16014v5 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) systems deployed in sensitive domains must provide interpretable evidence selection and robust safeguards again
arXiv:2603.07664v3 Announce Type: replace-cross Abstract: The reflective appearance, especially strong and typically near-field specular reflections, poses a fundamental challenge for accurate surface
arXiv:2606.02657v1 Announce Type: new Abstract: The standard generalization bounds assume that the training and deployment distributions are the same, or are static, and don't consider regime switchin
arXiv:2606.02606v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed as continuously evolving services, where frequent base-model updates may invalidate previously
arXiv:2606.02765v1 Announce Type: cross Abstract: Model dimension (d_{model}) is a fundamental hyperparameter in transformer language models, yet its role in setting the geometric limits of feature re
arXiv:2606.03817v1 Announce Type: new Abstract: Idioms can be analysed in terms of their decomposability, the extent to which constituent meanings contribute to the figurative whole. Decomposability i
arXiv:2606.03465v1 Announce Type: cross Abstract: Post-training compression is essential for deploying large language models (LLMs) under tight resource constraints. Tensor decompositions have emerged
arXiv:2502.08834v4 Announce Type: replace-cross Abstract: Deep generative models based on neural differential equations have become state-of-the-art for many generation tasks. These models rely on ODE
arXiv:2510.16392v3 Announce Type: replace Abstract: Personalized and continuous interactions are critical for LLM-based conversational agents, yet finite context windows and static parametric memory h
arXiv:2606.03074v1 Announce Type: new Abstract: Diffusion models achieve high-fidelity radio map construction through iterative denoising, yet their sampling cost limits practicality in dynamic wirele
arXiv:2606.02876v1 Announce Type: new Abstract: Randomized smoothing (RS) uses a smoothed classifier to provide architecture-agnostic certificates of ell_2 classification robustness, but its dependenc
arXiv:2511.02986v2 Announce Type: replace-cross Abstract: Computational modeling of single-cell gene expression is crucial for understanding cellular processes, but generating realistic expression pro
arXiv:2606.02886v1 Announce Type: cross Abstract: Deep learning weather models now match numerical weather prediction accuracy while running orders of magnitude faster, but produce deterministic forec
arXiv:2602.00423v3 Announce Type: replace Abstract: Single-cell integration workflows often construct low-dimensional cell embeddings and then refine them with post-hoc methods to reduce batch effects
arXiv:2606.03906v1 Announce Type: new Abstract: Simultaneous measurement of multiple omics modalities in single cells enables researchers to gain a more comprehensive understanding of cellular states
arXiv:2602.02890v2 Announce Type: replace Abstract: Model soups are strange and strangely effective combinations of parameters. They take a model (the stock), fine-tune it into multiple models (the in
arXiv:2606.03600v1 Announce Type: cross Abstract: Standard conformal prediction (CP) procedures are typically formulated in terms of p-values, but reliance on p-values alone limits flexibility, for ex
arXiv:2602.17063v2 Announce Type: replace-cross Abstract: Sub-bit model compression targets storage below one bit per weight; as magnitudes are aggressively compressed, the sign bit becomes a fixed-co
arXiv:2606.03796v1 Announce Type: cross Abstract: Signed spiking neurons carry richer information than standard spiking neurons. This work proposes a compact magnetic tunnel junction (MTJ)-based neuro
arXiv:2606.03169v1 Announce Type: cross Abstract: Recent song generation systems can synthesize realistic audio, yet generating complete songs remains challenging for two reasons. First, explicit song
arXiv:2606.03692v1 Announce Type: new Abstract: Recent AI agents can flexibly invoke skills to solve complex tasks, but their long-term improvement is fundamentally constrained by a lack of systematic
arXiv:2606.03102v1 Announce Type: new Abstract: Test-time scaling improves the reasoning performance of large language models but incurs substantial cost in both total computation and latency. Existin
arXiv:2601.14569v2 Announce Type: replace Abstract: Social understanding abilities are crucial for multimodal large language models (MLLMs) to interpret human social interactions. We introduce SOCIAL
arXiv:2606.03237v1 Announce Type: new Abstract: AI's central challenge is shifting from capability to coexistence. The dominant paradigm in AI research focuses on developing powerful agents that treat
arXiv:2606.03909v1 Announce Type: new Abstract: While 3D Gaussian Splatting has shown promising results in street scene reconstruction, existing methods require massive numbers of Gaussian primitives
arXiv:2606.02842v1 Announce Type: new Abstract: Multimodal spatial reasoning often relies on long chains of intermediate textual and visual thoughts, where accumulating visual tokens and dense cross-m
arXiv:2606.03359v1 Announce Type: cross Abstract: Speech emotion recognition is an important component of modern human-computer interaction systems. However, many state-of-the-art approaches rely on l
arXiv:2606.03545v1 Announce Type: new Abstract: Event-based tactile sensing offers low-latency signal acquisition for contact-rich robotic interaction. This paper investigates contact-angle estimation
arXiv:2606.03508v1 Announce Type: new Abstract: Printed circuit board (PCB) defect detection is an essential part of automated optical inspection (AOI); yet it remains challenging in practice because
arXiv:2606.03247v1 Announce Type: new Abstract: Document-grounded dialogue systems (DGDS) utilize knowledge from external documents to answer domain-specific user questions. Existing solutions typical
arXiv:2406.10407v3 Announce Type: replace-cross Abstract: Semidefinite programs (SDPs) and their solvers are powerful tools with many applications in machine learning and data science. Designing scala
arXiv:2606.02645v1 Announce Type: cross Abstract: Periodic target updates in Q-learning and soft target updates in actor-critic methods are empirically well established stabilization mechanisms, but t
arXiv:2606.03802v1 Announce Type: new Abstract: Objective: Consumer face camera remote photoplethysmography (rPPG) enables passive cardiovascular monitoring, but whether single-cycle waveform morpholo
arXiv:2606.02872v1 Announce Type: cross Abstract: This paper considers the problem of simultaneously controlling an interceptor's impact time and impact angle using its lateral acceleration as the sol
arXiv:2602.10387v2 Announce Type: replace-cross Abstract: Traditional query optimization relies on cost-based optimizers that estimate execution cost (e.g., runtime, memory, and I/O) using predefined
arXiv:2510.20372v4 Announce Type: replace-cross Abstract: Small influential data subsets can dramatically impact model conclusions, with a few data points overturning key findings. While recent work i
arXiv:2606.02601v1 Announce Type: new Abstract: Within-dataset class-split evaluation is widely used as a proxy for fully unconditional out-of-distribution anomaly detection. We show that this protoco
arXiv:2606.03839v1 Announce Type: new Abstract: Text-Attributed Graph (TAG) is an important type of graph structured data, where each node has a text description. TAG models usually train a Graph Neur
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. 5 key points in Trump’s new AI order Less than two weeks after
arXiv:2501.02173v2 Announce Type: replace-cross Abstract: The deployment of Large Language Models (LLMs) in recommender systems for predicting Click-Through Rates (CTR) necessitates a delicate balance
arXiv:2606.03358v1 Announce Type: new Abstract: Smart meter data can reveal sensitive socio-demographic characteristics of households, raising privacy concerns. While this risk has been demonstrated a
arXiv:2606.03645v1 Announce Type: cross Abstract: Large Language Models exhibit paradoxical fragility in fundamental arithmetic, implying a disconnect between internal computation and discrete output.
arXiv:2606.02758v1 Announce Type: cross Abstract: We introduce Lie groupoid equivariant neural networks as a specialization of recently proposed topological category-equivariant neural networks to the
arXiv:2606.02835v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) improve performance by generating explicit intermediate reasoning traces through increased test-time compute, yet the assu
Yann LeCun discusses a point from a Ted Chiang piece about the lack of claims regarding consciousness in recent AI systems like AlphaFold, Sora, and Midjourney, suggesting skepticism about attributing
arXiv:2506.00431v2 Announce Type: replace Abstract: Due to the proficiency of self-attention mechanisms (SAMs) in capturing dependencies in sequence modeling, several existing dynamic graph neural net
arXiv:2606.03459v1 Announce Type: cross Abstract: We study the assignment of local tonalities to chord sequences, a task useful for harmonic analysis, composition, and jazz-oriented improvisation. Sta
arXiv:2606.03655v1 Announce Type: new Abstract: Recent work in defeasible reasoning has seen notions of preferential semantics and entailment in the style of Kraus et al. applied to modal logics. Howe