Knowledge catalogue
arXiv:2512.07192v2 Announce Type: replace Abstract: Vector Quantization (VQ) based generative image compression has achieved remarkable perceptual quality. However, existing VQ codecs suffer from two
arXiv:2606.00875v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for tasks involving creative problem solving and idea generation. However, there is a lack of consens
arXiv:2503.07154v3 Announce Type: replace-cross Abstract: Generative pre-training is often framed through a false dichotomy between autoregressive models for discrete signals and diffusion models for
arXiv:2606.02231v1 Announce Type: cross Abstract: Temporal systems often exhibit non-stationary behaviour, such as seasonal climate variation or glucose fluctuations in patients with type-1 diabetes.
arXiv:2602.19066v2 Announce Type: replace-cross Abstract: Diffusion Language Models (DLMs) have recently achieved strong results in text generation. However, their multi-step sampling leads to slow in
arXiv:2507.23277v3 Announce Type: replace Abstract: Feed-forward 3D modeling has emerged as a promising approach for rapid and high-quality 3D reconstruction. In particular, directly generating explic
arXiv:2606.00872v1 Announce Type: new Abstract: AI-generated image detection is a moving-target problem: detectors trained on one generator often fail when a new generator appears, and only a few labe
arXiv:2606.00077v1 Announce Type: cross Abstract: Recently, Belief-Attention ite{Guoqiang25BeliefAttention} has been proposed by first performing an orthogonal projection of the softmax-based weighted
arXiv:2606.02532v1 Announce Type: new Abstract: Analyzing microstructural defects in transmission electron microscopy (TEM) images, particularly in irradiated metal alloys, is often limited by the ava
arXiv:2606.00161v1 Announce Type: cross Abstract: The detection of intrusions in IoT-based networks poses challenges that cannot be overcome using traditional machine learning methods. Perhaps the big
arXiv:2606.00556v1 Announce Type: new Abstract: Visual grounding aims to locate image regions that correspond to natural language descriptions and is a key component of interpretable vision systems. I
arXiv:2606.01711v1 Announce Type: new Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have achieved remarkable success in vision-language tasks, yet the quadratic computation
arXiv:2606.01626v1 Announce Type: new Abstract: Planning with a learned latent world model is a promising route to control from raw pixels, but a strong world model alone is not enough. We show this e
arXiv:2606.00520v1 Announce Type: cross Abstract: Many stochastic gradient methods are believed not to converge when the noise in stochastic gradients has only a finite p-th moment for pinleft(1,2righ
arXiv:2606.00703v1 Announce Type: cross Abstract: Low-precision pretraining (FP8, MXFP4, NVFP4) is now standard for frontier language models, yet the literature is almost entirely achievability -- alg
arXiv:2606.02453v1 Announce Type: cross Abstract: Despite the remarkable fidelity of generative models, they frequently suffer from mode collapse. Existing strategies for enhancing diversity predomina
arXiv:2606.00289v1 Announce Type: new Abstract: Quantization is a fundamental tool used to compress datasets, neural network weights, and memory usage in a range of computational tasks. Many downstrea
arXiv:2606.02486v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models generalize across static manipulation but fail when objects move during task execution. They map the current observa
arXiv:2503.22939v4 Announce Type: replace Abstract: The integration of heterogeneous multi-omics datasets at a systems level remains a central challenge for developing analytical and computational mod
arXiv:2410.14483v3 Announce Type: replace-cross Abstract: Reliable uncertainty quantification for causal effects is crucial in high-stakes applications, but remains challenging when the target is an e
arXiv:2606.00296v1 Announce Type: cross Abstract: Neural operators are often reported to exhibit zero-shot super-resolution, a phenomenon in which a model trained on coarse grids produces accurate pre
arXiv:2606.02101v1 Announce Type: cross Abstract: This paper proposes a method of creating synthetic data (SD) that will have two important advantages for the user compared to other methods currently
arXiv:2511.09190v2 Announce Type: replace Abstract: Hyperparameter Optimization (HPO) can lift the burden of tuning hyperparameters (HPs) of neural networks. HPO algorithms from the Population Based T
arXiv:2606.00532v1 Announce Type: new Abstract: Context engineering can improve large language models without updating their weights, but mathematical reasoning exposes a key limitation: feedback accu
arXiv:2603.20176v3 Announce Type: replace Abstract: Recent work has shown that neural networks can perform 3D tasks such as Novel View Synthesis (NVS) without explicit 3D reconstruction. Even so, we a
arXiv:2606.00260v1 Announce Type: new Abstract: Human Activity Recognition (HAR) from ambient sensors enables smart-home applications such as health monitoring and assisted living. In realistic deploy
arXiv:2606.00726v1 Announce Type: new Abstract: Strong reasoning depends not only on model knowledge but also on how effectively cognitive behaviors are deployed during generation. Existing methods of
arXiv:2606.01432v1 Announce Type: new Abstract: Accurate modeling of leaf spectral reflectance from physiological and biochemical traits is essential for advancing remote sensing applications in plant
arXiv:2606.01950v1 Announce Type: cross Abstract: World models enable intelligent agents to predict the consequences of their actions on the environment. In this paper, we propose Multi Rigid Object G
arXiv:2606.01436v1 Announce Type: new Abstract: The growing capabilities of large language models (LLMs) have led to the saturation of many benchmarks and training datasets used to improve them. Motiv
arXiv:2509.24627v2 Announce Type: replace Abstract: Embedding physical intuition into network architectures allows the learning of dynamics that enforce fundamental properties, such as energy conserva
arXiv:2606.01698v1 Announce Type: new Abstract: Deep learning has revolutionized medical image analysis, delivering exceptional diagnostic accuracy across diverse applications. Yet, the lack of interp
arXiv:2606.01021v1 Announce Type: new Abstract: Recent developments in 3D shape representation opened new possibilities for generating detailed 3D shapes. Despite these advances, there are few studies
arXiv:2503.03137v3 Announce Type: replace Abstract: Constructive neural combinatorial optimization (NCO) offers a promising paradigm for solving vehicle routing problems (VRPs) by directly learning to
arXiv:2603.26028v2 Announce Type: replace Abstract: Medical Visual Question Answering (MedVQA) models often exhibit limited generalization due to reliance on dataset-specific correlations, such as rec
arXiv:2603.02238v2 Announce Type: replace Abstract: Length generalization is a key property of a learning algorithm that enables it to make correct predictions on inputs of any length, given finite tr
arXiv:2405.14782v3 Announce Type: replace Abstract: Reliable evaluation of language models (LMs) remains an open challenge. Re- searchers and engineers face methodological issues such as the sensitivi
arXiv:2606.00677v1 Announce Type: new Abstract: Fourier Neural Operators are often assumed to generalize across spatial resolutions, enabling training on a coarse grid and deployment on a finer grid.
arXiv:2603.26779v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, yet they struggle with spatial tasks that require mental sim
arXiv:2606.00063v1 Announce Type: new Abstract: Systems moving in low Reynolds number fluid regimes are known to be governed by a ``motility map'' which linearly relates their shape change rates to th
arXiv:2606.00613v1 Announce Type: cross Abstract: Watermarking should identify language-model output without degrading quality or limiting verification to the model provider. Multilingual deployment m
arXiv:2606.00418v1 Announce Type: new Abstract: Soft robotics is increasingly explored in artistic contexts, where tactile interaction provides audiences with embodied engagement beyond visual or audi
arXiv:2602.23881v2 Announce Type: replace-cross Abstract: Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to propose candidate t
arXiv:2606.00022v1 Announce Type: cross Abstract: Humor generation remains difficult not only because producing fluent, novel jokes is hard, but because 'funny' is audience-dependent and supervision i
arXiv:2606.01128v1 Announce Type: new Abstract: Communication overhead is a crucial bottleneck in scalable distributed learning. While existing methods aim to efficiently utilize data points, such as
arXiv:2606.00771v1 Announce Type: cross Abstract: A simple way to improve the performance of almost any machine learning model is not to train a single but several models with diverse algorithms which
arXiv:2606.02553v1 Announce Type: new Abstract: Autoregressive (AR) video diffusion enables variable-length synthesis, but long-horizon generation often suffers from accumulated errors and identity dr
arXiv:2410.12325v2 Announce Type: replace Abstract: In this paper, we study a fundamental design problem in pretraining Large Language Models (LLMs) for low-resource language regimes. Existing works a
arXiv:2606.00060v1 Announce Type: cross Abstract: This paper investigates whether machine learning forecasts of hourly BTC-USDT returns can be converted into economically meaningful trading performanc
arXiv:2606.02004v1 Announce Type: new Abstract: Consumer-price measurement increasingly draws on alternative data sources -- scanner, web-scraped, and transaction/receipt data. A recurring obstacle is
arXiv:2606.00666v1 Announce Type: cross Abstract: Transition metal complexes are central to catalysis, drug design, and materials science, with relevant properties strongly sensitive to their three-di
arXiv:2606.00672v1 Announce Type: new Abstract: Financial exploitation is a growing concern for people with Alzheimer's disease, especially during periods of reduced cognitive stability. Conventional
arXiv:2606.00888v1 Announce Type: cross Abstract: Dynamic Sparse Training (DST) offers a promising paradigm for improving the training and inference efficiency of deep neural networks; however, we fin
arXiv:2606.01655v1 Announce Type: cross Abstract: The Bayesian paradigm offers principled tools for sequential decision-making under uncertainty, but its reliance on a probabilistic model for all para
arXiv:2603.06989v3 Announce Type: replace Abstract: This paper introduces MipSLAM, a frequency-aware 3D Gaussian Splatting (3DGS) SLAM framework capable of high-fidelity anti-aliased novel view synthe
arXiv:2502.00753v4 Announce Type: replace-cross Abstract: Smoothness is crucial for attaining fast rates in first-order optimization. However, many optimization problems in modern machine learning inv
arXiv:2606.00819v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved strong performance across diverse natural language tasks, yet their outputs often suffer from hallucinations
arXiv:2602.10623v2 Announce Type: replace-cross Abstract: Reward models learned from human preferences are central to aligning large language models (LLMs) via reinforcement learning from human feedba
arXiv:2606.00909v1 Announce Type: cross Abstract: This work presents MLLM-Microscope, a novel system designed for analyzing the hidden representations within Multimodal Large Language Models (MLLMs).
arXiv:2604.02941v2 Announce Type: replace Abstract: Speech-driven three-dimensional (3D) facial animation synthesis aims to build a mapping from one-dimensional (1D) speech signals to time-varying 3D