Knowledge catalogue
arXiv:2512.08309v4 Announce Type: replace Abstract: For decades, procedural worlds have been built on procedural noise functions such as Perlin noise, which are fast and infinite, yet fundamentally li
arXiv:2605.02364v1 Announce Type: new Abstract: Upweighting high-quality data in LLM pretraining often improves performance, but in datalimited regimes, especially under overtraining, stronger upweigh
arXiv:2605.01402v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) struggle with numerical regression under long-tailed target distributions. Token-level supervised fine-tuning (
arXiv:2605.00572v1 Announce Type: new Abstract: Algorithm performance in combinatorial optimization is highly sensitive to parameter settings, while a single globally tuned configuration often fails t
arXiv:2512.21788v3 Announce Type: replace Abstract: Parameter-Efficient Fine-Tuning of Diffusion Transformers (DiTs) for diverse, multi-conditional tasks often suffers from task interference when usin
arXiv:2605.01409v1 Announce Type: cross Abstract: The growing availability of health-related instructional videos creates new opportunities for clinical training, patient rehabilitation, and health ed
arXiv:2503.09559v3 Announce Type: replace-cross Abstract: We introduce interlaced R2D2 (iR2D2), a DNN series paradigm for scalable image reconstruction from accelerated non-Cartesian k-space acquisiti
arXiv:2605.01036v1 Announce Type: new Abstract: This paper tackles the problem of physics-aware human motion synthesis in a dynamic scene. Unlike existing works which mainly tend to generate physicall
arXiv:2605.01097v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have led to the development of AI-powered tutoring systems that provide interactive support via dialogue
arXiv:2605.00940v1 Announce Type: new Abstract: A new interpretable experiential learning model based on state history and global feedback is presented. It is capable of learning a behavioral model re
arXiv:2605.00882v1 Announce Type: new Abstract: Remote Photoplethysmography (rPPG) enables convenient non-contact physiological measurement. Existing Self-Supervised Learning (SSL) methods commonly fa
arXiv:2601.06035v2 Announce Type: replace-cross Abstract: The release of SAM 3D Body is a recent development in human mesh recovery, demonstrating improved performance in producing clean, topologicall
arXiv:2412.15251v3 Announce Type: replace Abstract: Multimodal large language models (MLLMs) are effective at capturing the semantics of short video content; however, they often fail to attend to the
arXiv:2605.02392v1 Announce Type: new Abstract: Novelty assessment is a critical yet complex task in the examination process for patent acceptance, requiring examiners to determine whether an inventio
arXiv:2602.07238v2 Announce Type: replace-cross Abstract: Do leading LLM developers possess a proprietary ``secret sauce'', or is LLM performance driven by scaling up compute? Using training and bench
arXiv:2605.02597v1 Announce Type: new Abstract: Fourier Neural Operators are deep learning models that learn mappings between function spaces and can be used to learn and solve partial differential eq
arXiv:2512.04032v3 Announce Type: replace Abstract: We present jina-vlm, a token-efficient 2.4B parameter vision-language model that achieves state-of-the-art multilingual VQA performance among open 2
arXiv:2605.01742v1 Announce Type: new Abstract: Vision Transformers (ViTs) have achieved strong performance in visual recognition, yet their deployment in resource-constrained industrial environments
arXiv:2605.02190v1 Announce Type: new Abstract: Kolmogorov-Arnold networks (KANs) offer a potent combination of accuracy and interpretability, thanks to their compositions of learnable univariate acti
arXiv:2510.10245v2 Announce Type: replace-cross Abstract: Adaptive experiments improve efficiency by adjusting treatment assignments based on past outcomes, but this adaptivity breaks the i.i.d. assum
arXiv:2510.13048v2 Announce Type: replace Abstract: We introduce Kinematic Kitbashing, an optimization framework that synthesizes articulated 3D objects by assembling reusable parts conditioned on an
arXiv:2404.10370v3 Announce Type: replace Abstract: Open set recognition (OSR) is a critical aspect of machine learning, addressing the challenge of detecting novel classes during inference. Within th
arXiv:2602.12873v4 Announce Type: replace-cross Abstract: Generative social robots (GSRs) powered by large language models enable adaptive, conversational tutoring but also introduce risks such as mis
arXiv:2605.02288v1 Announce Type: new Abstract: Automated laboratories hold the promise of accelerating scientific discovery, yet their deployment is bottlenecked by the difficulty of designing safe a
arXiv:2604.17465v2 Announce Type: replace Abstract: We provide evidence that language models can detect, localize and, to a certain degree, verbalize the difference between perturbations applied to th
arXiv:2605.02866v1 Announce Type: new Abstract: Rural thematic road network construction aims to extract topological road structures from movement trajectory images of agricultural machinery. However,
arXiv:2502.03814v5 Announce Type: replace Abstract: The rapid advancement of Large Language Models (LLMs) has opened new possibilities in Multi-Robot Systems (MRS), enabling enhanced communication, ta
arXiv:2605.02027v1 Announce Type: new Abstract: This paper introduces the use of per-class regularization hyperparameters in Gabriel graph-based binary classifiers. We demonstrate how the quality inde
arXiv:2605.02739v1 Announce Type: new Abstract: Dual-system Vision-Language-Action (VLA) models achieve state-of-the-art robotic manipulation but are bottlenecked by the VLM backbone, which must execu
arXiv:2605.00874v1 Announce Type: new Abstract: The rapid proliferation of AI-powered video generation systems has introduced significant challenges in content moderation, particularly with respect to
arXiv:2505.20340v3 Announce Type: replace Abstract: Understanding how latent representations evolve during generation is a central open problem in large language model interpretability. We introduce e
arXiv:2605.00899v1 Announce Type: new Abstract: We present LatentDiff, a scalable framework for semantic dataset comparison that operates directly in the latent space of pretrained vision encoders. By
arXiv:2605.01731v1 Announce Type: new Abstract: Platooning of connected and automated vehicles provides significant benefits in terms of energy efficiency, traffic throughput, and, most critically, sa
arXiv:2605.01058v1 Announce Type: cross Abstract: Layer-aligned distillation and convergence-based early exit represent two predominant computational efficiency paradigms for transformer inference; ye
arXiv:2605.01973v1 Announce Type: new Abstract: Conventional LLMs may suffer from corpus heterogeneity and subtle condition changes. While finetuning can create the catastrophe forgetting issue, appli
arXiv:2601.08116v2 Announce Type: replace Abstract: Tropical cyclones are dangerous natural hazards, but their hazard is challenging to quantify directly from historical datasets due to limited datase
arXiv:2509.10468v2 Announce Type: replace-cross Abstract: Recent advances in generative recommenders adopt a two-stage paradigm: items are first tokenized into semantic IDs using a pretrained tokenize
arXiv:2605.01089v1 Announce Type: new Abstract: The ensemble Gaussian mixture filter (EnGMF) is a powerful, convergent particle filter capable of medium-to-high dimensional non-linear filtering. The E
arXiv:2605.02699v1 Announce Type: cross Abstract: Learning data-efficient object dynamics models for robotic manipulation remains challenging, especially for deformable objects. A popular approach is
arXiv:2605.01046v1 Announce Type: new Abstract: LoRA adapts large language models (LLMs) by restricting updates to low-rank subspaces of pre-trained weights. While this substantially reduces training
arXiv:2605.01835v1 Announce Type: new Abstract: Nonlinear coupled systems are ubiquitous in science and engineering. The analysis and modeling of such systems is challenging due to their high dimensio
arXiv:2510.03599v2 Announce Type: replace Abstract: We present a unified framework for multi-task locomotion and manipulation policy learning grounded in a contact-explicit representation. Instead of
arXiv:2503.04496v2 Announce Type: replace-cross Abstract: In this work we study indoor scene object placement. Given a 3D indoor scene and an object, the task is to predict placement locations within
arXiv:2605.01096v1 Announce Type: new Abstract: Reinforcement Learning (RL) has the potential to enable robots with fast, nonlinear, and unstable dynamics to reach the limits of their performance. How
arXiv:2605.01591v1 Announce Type: cross Abstract: Neural Ranking Models (NRMs) are central to modern information retrieval but remain highly vulnerable to adversarial manipulation. Existing attacks of
arXiv:2605.01735v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly deployed in real-world systems, they must support post-hoc removal of specific content to meet privacy
arXiv:2509.21173v5 Announce Type: replace Abstract: Vision-Language Models (VLMs) such as CLIP have revolutionized zero-shot classification and safety-critical tasks, including Out-of-Distribution (OO
arXiv:2605.02457v1 Announce Type: new Abstract: Information disorder is a challenging phenomenon that affects society at large. This phenomenon entails the diffusion of misleading, misinforming, and h
arXiv:2605.01874v1 Announce Type: new Abstract: The performance of machine learning models often relies on large labeled datasets; however, data collected from diverse sources can contain label noise.
arXiv:2412.02408v3 Announce Type: replace-cross Abstract: The advent of smart contracts has enabled the rapid rise of Decentralized Finance (DeFi) on the Ethereum blockchain, offering substantial rewa
arXiv:2605.00913v1 Announce Type: new Abstract: Sensor-based Human Activity Recognition (HAR) has attracted increasing attention in medical and healthcare monitoring, particularly with the growth of I
arXiv:2601.17185v2 Announce Type: replace Abstract: We propose a new method for few-shot 3D reconstruction that integrates global and local frequency regularization to stabilize geometry and preserve
arXiv:2605.00879v1 Announce Type: new Abstract: Rehabilitation aims to help patients with limited mobility regain their physical abilities through targeted movements, exercises, stimulation, and other
arXiv:2605.02809v1 Announce Type: new Abstract: Long-term autonomy requires robust navigation in environments subject to dynamic and static changes, as well as adverse weather conditions. Teach-and-Re
arXiv:2605.01478v1 Announce Type: new Abstract: Online High-Definition (HD) map construction is a key component of autonomous driving. Recent methods rely on multi-view camera images for cost-effectiv
arXiv:2202.10873v4 Announce Type: replace-cross Abstract: Robust and efficient interpretation of QSAR methods is quite useful to validate AI prediction rationales with subjective opinion (chemist or b
arXiv:2510.06516v2 Announce Type: replace Abstract: Limited-angle electron tomography aims to reconstruct 3D shapes from 2D projections of Transmission Electron Microscopy (TEM) within a restricted ra
arXiv:2605.01192v1 Announce Type: new Abstract: Two recent approaches to computation in superposition reach different recursive capacity regimes: Hanni et al. certify ilde{O}(d^{3/2}) computable featu
arXiv:2605.01711v1 Announce Type: new Abstract: Existing research largely attributes the global sequence modeling capability of Transformers to the explicit computation of attention weights, a process
arXiv:2605.02772v1 Announce Type: new Abstract: While linear-complexity attention mechanisms offer a promising alternative to Softmax attention for overcoming the quadratic bottleneck, training such m