How Mobile World Model Guides GUI Agents?
arXiv:2605.10347v1 Announce Type: new Abstract: Recent advances in vision-language models have enabled mobile GUI agents to perceive visual interfaces and execute user instructions, but reliable predi
Knowledge catalogue
arXiv:2605.10347v1 Announce Type: new Abstract: Recent advances in vision-language models have enabled mobile GUI agents to perceive visual interfaces and execute user instructions, but reliable predi
arXiv:2605.08348v1 Announce Type: new Abstract: The circuits framework in mechanistic interpretability aims to identify causally important sparse subgraphs of model components, typically evaluated by
This article examines how open-source AI model ecosystems create compounding effects through community contributions, fine-tuning, and iterative improvements that accelerate innovation and accessibili
arXiv:2605.10199v1 Announce Type: new Abstract: Full-duplex spoken dialogue requires a model to keep listening while generating its own spoken response. This is challenging for large language models (
arXiv:2605.08817v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) recently thrives in large language model (LLM) reasoning tasks. However, the reward sparsity and t
arXiv:2605.09899v1 Announce Type: cross Abstract: Cross-modal knowledge distillation has emerged as an effective strategy for integrating point cloud and image features in 3D perception tasks. However
arXiv:2605.10628v1 Announce Type: new Abstract: Few-shot anomaly detection (FSAD) has made significant strides, yet existing methods still face critical challenges: (i) dependence on task- or dataset-
arXiv:2605.10164v1 Announce Type: new Abstract: Dense Associative Memory (DenseAM) is a promising family of AI architectures that is represented by a neural network performing temporal dynamics on an
arXiv:2605.10100v1 Announce Type: cross Abstract: We introduce HYPERPOSE, a novel 3D human pose estimation framework that performs spatio-temporal reasoning entirely within the Lorentz model of hyperb
arXiv:2605.08254v1 Announce Type: cross Abstract: As foundation models grow in capability, the ability to efficiently and reliably control their behavior becomes critical. Fine-tuning these models can
arXiv:2605.10560v1 Announce Type: new Abstract: This paper describes our system to SemEval-2026 Task 3 Track A Subtask 1 on Dimensional Aspect Sentiment Regression (DimASR). We propose a lightweight a
arXiv:2605.10407v1 Announce Type: new Abstract: Modern LLM APIs often reveal only top-K logit scores and censor the remaining vocabulary. We study the per-position distribution-recovery limits of this
arXiv:2603.08558v2 Announce Type: replace Abstract: Learning compact state representations in Markov Decision Processes (MDPs) has proven crucial for addressing the curse of dimensionality in large-sc
arXiv:2601.20477v3 Announce Type: replace Abstract: We study the training dynamics of neural classifiers through the lens of binary hypothesis testing. We re-formalize classification as a collection o
arXiv:2512.02012v2 Announce Type: replace Abstract: MeanFlow (MF) has recently been established as a framework for one-step generative modeling. However, its ``fastforward'' nature introduces key chal
arXiv:2605.10149v1 Announce Type: new Abstract: Temporal action segmentation (TAS) divides untrimmed videos into labeled action segments. While fully supervised methods have advanced the field, challe
In KAME, a fast speech model starts replying instantly, while a backend LLM runs in parallel to inject deep knowledge on the fly. It’s a completely different way to approach conversational AI, making
arXiv:2512.21587v2 Announce Type: replace-cross Abstract: Spatial photonic Ising machines offer a novel optical platform for optimization and spin-model simulation, but existing diffraction-based sche
arXiv:2605.10269v1 Announce Type: new Abstract: Maritime object detection is critical for the safe navigation of unmanned surface vessels (USVs), requiring accurate recognition of obstacles from small
arXiv:2605.09977v1 Announce Type: new Abstract: Spatio-temporal fetal brain atlases are important for characterizing normative neurodevelopment and identifying congenital anomalies. However, existing
arXiv:2605.10518v1 Announce Type: cross Abstract: Masked Diffusion Models (MDMs) have emerged as a promising alternative to autoregressive models in language modeling, offering the advantages of paral
arXiv:2605.09273v1 Announce Type: new Abstract: We study online multicalibration beyond the worst-case. We give a single, efficient algorithm which dynamically interpolates between benign and worst-ca
arXiv:2412.01324v4 Announce Type: replace Abstract: This work presents a novel and efficient nonlinear programming framework that tightly integrates hierarchical decision-making with whole-body invers
arXiv:2605.10627v1 Announce Type: cross Abstract: Coreference resolution is typically evaluated using aggregate statistical metrics such as CoNLL-F1, which measure structural overlap between predicted
arXiv:2605.10796v1 Announce Type: new Abstract: Machine learning has become increasingly prevalent in football performance analysis, yet most studies prioritize predictive accuracy while implicitly as
arXiv:2605.10633v1 Announce Type: cross Abstract: Fine-tuning Large Language Models (LLMs) on benign narrow data can sometimes induce broad harmful behaviors, a vulnerability termed emergent misalignm
arXiv:2605.09238v1 Announce Type: cross Abstract: Muon and related norm-constrained matrix optimizers have become central to large-scale learning problems. They are formulated as a linear maximization
arXiv:2605.09439v1 Announce Type: new Abstract: Generative models are powerful tools for sampling from a learned distribution P(Y mid X), and inverse-design methods invert this map to find an input x
arXiv:2605.10684v1 Announce Type: cross Abstract: Data selection studies the problem of identifying high-quality subsets of training data. While some existing works have considered selecting the subse
arXiv:2605.10551v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have achieved strong results in molecular property prediction, but polymers present distinct challenges: labeled datasets a
arXiv:2605.10178v1 Announce Type: cross Abstract: Adaptive behavior requires the brain to transition between distinct contexts while maintaining representations of prior experience. The ability to rec
arXiv:2605.08587v1 Announce Type: cross Abstract: Long-context language modeling remains central to modern sequence modeling, but the quadratic cost of Transformer attention makes scaling computationa
arXiv:2605.10727v1 Announce Type: new Abstract: We propose kernel-gradient drifting, a one-step generative modeling framework that replaces the fixed Euclidean displacement direction in drifting model
arXiv:2605.09877v1 Announce Type: cross Abstract: We present Key-Value Means ('KVM'), a novel block-recurrence for attention that can accommodate either fixed-size or growing state. Equipping a strong
arXiv:2605.09386v1 Announce Type: cross Abstract: Metric-induced discrete flow matching (MI-DFM) exploits token-latent geometry for discrete generation, but its practical use is limited by two issues:
arXiv:2605.09213v1 Announce Type: cross Abstract: We study causal self-attention dynamics -- a toy model for decoder Transformers -- which we interpret as a non-exchangeable interacting particle syste
arXiv:2605.10253v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) is a widely adopted paradigm for enhancing LLMs in medical applications by incorporating expert multimodal knowle
arXiv:2605.08806v1 Announce Type: new Abstract: Existing 2D-3D lifting human pose estimation methods have achieved strong performance. But the utilization of historical pose representations across net
arXiv:2605.09994v1 Announce Type: cross Abstract: Modern Large Foundation Model (LFM) training has transformed the data pipeline from a static ingestion layer into a dynamic component that must co-evo
arXiv:2605.09060v1 Announce Type: new Abstract: Multilingual vision-language models exhibit systematic performance gaps across languages, but the mechanism remains ambiguous: cross-language divergence
arXiv:2602.09297v2 Announce Type: replace Abstract: Transformers update token representations through multi-head attention and residual connections as X leftarrow X + sum_{i} P^{(i)}XW_{V_i}W_{o_i}, w
arXiv:2605.09204v1 Announce Type: new Abstract: Backpropagation is inherently sequential across depth, creating an O(K)-deep dependency chain that bottlenecks parallel training. While parallel-scan fo
arXiv:2605.08552v1 Announce Type: cross Abstract: Independent Component Analysis (ICA) is a foundational tool for unsupervised representation learning, yet its high-dimensional theory remains largely
arXiv:2605.08209v1 Announce Type: new Abstract: Deep learning methods are widely used under diverse resource constraints, resulting in models of varying sizes, such as the Vision Transformer (ViT) ser
arXiv:2605.09993v1 Announce Type: new Abstract: Graph foundation models (GFMs), pretrained on massive graph data, have transformed graph machine learning by supporting general-purpose reasoning across
arXiv:2605.10855v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have demonstrated remarkable progress in chart understanding, largely driven by supervised fine-tuning (SFT) on increasing
arXiv:2605.08506v1 Announce Type: new Abstract: Robust optimization (RO) provides a principled framework for decision-making under uncertainty, but its performance critically depends on the choice of
arXiv:2511.17994v2 Announce Type: replace Abstract: We study differentially private model training with stochastic gradient descent under learning rate scheduling and correlated noise. Although correl
arXiv:2605.09718v1 Announce Type: cross Abstract: Many systems in physics, engineering, and biology exhibit multiscale stochastic dynamics, where low-dimensional slow variables evolve under the influe
arXiv:2303.05307v2 Announce Type: replace-cross Abstract: We study general-sum, multi-player stochastic games with transferable utility, motivated by settings where agents can use side payments to mak
arXiv:2605.09964v1 Announce Type: new Abstract: Protein-protein interactions (PPIs) are fundamental to cellular function and disease mechanisms. Current learning-based PPI predictors focus on learning
arXiv:2605.08811v1 Announce Type: cross Abstract: This paper investigates the learning theory of Transformer networks for regression tasks on the compact Euclidean domain [0,1]^d and d-dimensional com
arXiv:2601.21410v3 Announce Type: replace-cross Abstract: Large language models (LLMs) encode rich semantic knowledge that can be useful for supervised learning, but their outputs are unreliable as st
arXiv:2605.06394v1 Announce Type: cross Abstract: These lecture notes introduce some topics of classical statistical physics, particularly those that are relevant for neural networks and deep learning
arXiv:2512.23025v2 Announce Type: replace-cross Abstract: Multimodal health sensing offers rich behavioral signals for assessing mental health, yet translating these numerical time-series measurements
arXiv:2509.25742v4 Announce Type: replace Abstract: Graph Contrastive Learning (GCL) has shown strong promise for unsupervised graph representation learning, yet its effectiveness on heterophilic grap
arXiv:2605.09764v1 Announce Type: cross Abstract: LLM-guided evolutionary methods such as AlphaEvolve have proven effective in domains like math, systems research, and algorithmic discovery, but their
arXiv:2503.14434v3 Announce Type: replace-cross Abstract: Automated feature engineering plays a critical role in improving predictive model performance for tabular learning tasks. Traditional automate
arXiv:2605.08850v1 Announce Type: cross Abstract: We design Local LMO - a new projection-free gradient-type method for constrained optimization. The key algorithmic idea is to replace the global linea
arXiv:2605.09830v1 Announce Type: cross Abstract: We present Loom, an outfit recommendation system that combines neural embedding retrieval with structured domain scoring to generate complete, coheren