arXiv Research Digest

To embed domain-specific or specialized knowledge into pre-trained foundation models, fine-tuning using techniques such as parameter efficient fine-tuning (e.g....

We introduce DreamerAD, the first latent world model framework that enables efficient reinforcement learning for autonomous driving by compressing diffusion sam...

Generative Retrieval (GR) has emerged as a promising paradigm for modern search systems. Compared to multi-stage cascaded architecture, it offers advantages suc...

Autonomous mobile GUI agents have attracted increasing attention along with the advancement of Multimodal Large Language Models (MLLMs). However, existing metho...

Accurate subseasonal weather forecasting remains a major challenge due to the inherently chaotic nature of the atmosphere, which limits the predictive skill of ...

Document parsing is a fine-grained task where image resolution significantly impacts performance. While advanced research leveraging vision-language models bene...

Vision--Language--Action (VLA) policies have shown strong progress in mapping language instructions and visual observations to robotic actions, yet their reliab...

Self-distillation has emerged as an effective post-training paradigm for LLMs, often improving performance while shortening reasoning traces. However, in mathem...

We introduce Latent-WAM, an efficient end-to-end autonomous driving framework that achieves strong trajectory planning through spatially-aware and dynamics-info...

Composer 2 is a specialized model designed for agentic software engineering. The model demonstrates strong long-term planning and coding intelligence while main...

Enes The proposed architecture is a mixture of experts, which allows for the model entities, such as the causal relationships, to be further parameterized. More...

The advent of "OCR 2.0" and large-scale vision-language models (VLMs) has set new benchmarks in text recognition. However, these unified architectures often com...

Scalable Vector Graphics (SVG) are an essential format for technical illustration and digital design, offering precise resolution independence and flexible sema...

Scene text editing seeks to modify textual content in natural images while maintaining visual realism and semantic consistency. Existing methods often require t...

Constrained optimization in high-dimensional black-box settings is difficult due to expensive evaluations, the lack of gradient information, and complex feasibi...

Research on explainable AI (XAI) has frequently focused on explaining model predictions. More recently, methods have been proposed to explain prediction uncerta...

Agentic Variation Operators (AVO) are a new family of evolutionary variation operators that replace the fixed mutation, crossover, and hand-designed heuristics ...

Miscalibrated confidence scores are a practical obstacle to deploying AI in clinical settings. A model that is always overconfident offers no useful signal for ...

Real-world fine-grained visual retrieval often requires discovering a rare concept from large unlabeled collections with minimal supervision. This is especially...

Recent advances in large language models (LLMs) and LLM-based agents have substantially improved the capabilities of automated theorem proving. However, for pro...

Recent Deepfake Video Detection (DFD) studies have demonstrated that pre-trained Vision-Language Models (VLMs) such as CLIP exhibit strong generalization capabi...

Speaker verification at large scale remains an open challenge as fixed-margin losses treat all samples equally regardless of quality. We hypothesize that mislab...

Understanding how biomarker distributions evolve over time is a central challenge in digital health and chronic disease monitoring. In diabetes, changes in the ...

Generating realistic 3D hand motion from natural language is vital for VR, robotics, and human-computer interaction. Existing methods either focus on full-body ...

Privacy and algorithmic fairness have become two central issues in modern machine learning. Although each has separately emerged as a rapidly growing research a...

Modern software systems heavily rely on third-party dependencies, making software supply chain security a critical concern. We introduce the concept of software...

Personalized Federated Learning (PFL) aims to deliver effective client-specific models under heterogeneous distributions, yet existing methods suffer from shall...

In scientific computing, the formulation of numerical discretisations of partial differential equations (PDEs) as untrained convolutional layers within Convolut...

Neural operator learning directly constructs the mapping relationship from the equation parameter space to the solution space, enabling efficient direct inferen...

Every API token you spend is your accumulated wealth; once you can prove its value and the effort behind it, you can resell it. As autonomous agents repeatedly ...

The advent of quantum computing will pose great challenges to the current communication systems, requiring essential changes in the establishment of security as...

Deep learning models for time series imputation are now essential in fields such as healthcare, the Internet of Things (IoT), and finance. However, their deploy...

Increasing demands for adaptability, privacy, and security at the edge have persistently pushed the frontiers for a new generation of machine learning (ML) algo...

In the IoT era, information is more and more frequently picked up by connected smart sensors with increasing, though limited, storage, communication and computa...

Learning representations from multiplex graphs, i.e., multi-layer networks where nodes interact through multiple relation types, is challenging due to the entan...

We introduce the Multilevel Euler-Maruyama (ML-EM) method compute solutions of SDEs and ODEs using a range of approximators $f^1,\dots,f^k$ to the drift $f$ wit...

Retrieval-augmented generation (RAG) systems are increasingly used to analyze complex policy documents, but achieving sufficient reliability for expert usage re...

While large-scale pretraining has revolutionized language modeling, its potential remains underexplored in healthcare with structured electronic health records ...

Activation steering has emerged as a powerful tool to shape LLM behavior without the need for weight updates. While its inherent brittleness and unreliability a...

LLM agents like Claude Code can not only write code but also be used for autonomous AI research and engineering \citep{rank2026posttrainbench, novikov2025alphae...

The practical deployment of nonlinear model predictive control (NMPC) is often limited by online computation: solving a nonlinear program at high control rates ...

Learning-based models for fluid dynamics often operate in unconstrained function spaces, leading to physically inadmissible, unstable simulations. While penalty...

Uniform laws of large numbers form a cornerstone of Vapnik--Chervonenkis theory, where they are characterized by the finiteness of the VC dimension. In this wor...

Accurate forecasting of state-of-health (SOH) is essential for ensuring safe and reliable operation of lithium-ion cells. However, existing models calibrated on...

Computer-use agents (CUAs) hold great promise for automating complex desktop workflows, yet progress toward general-purpose agents is bottlenecked by the scarci...

Parametric roll is a rare but high-consequence instability that can trigger abrupt regime changes in ship response, including pronounced shifts in roll statisti...

OpenClaw has rapidly established itself as a leading open-source autonomous agent runtime, offering powerful capabilities including tool integration, local file...

We propose a neural network model for contextual regression in which the regression model depends on contextual features that determine the active submodel and ...

One of the many fairness definitions pursued in recent recommender system research targets mitigating demographic information encoded in model representations. ...

The theory of Local Intrinsic Dimensionality (LID) has become a valuable tool for characterizing local complexity within and across data manifolds, supporting a...

Regenerating singing voices with altered lyrics while preserving melody consistency remains challenging, as existing methods either offer limited controllabilit...

Virtual influencers~(VIs) -- digitally synthetic social-media personas -- attract audiences whose discourse appears qualitatively different from discourse aroun...

Graphic icons are a cornerstone of modern design workflows, yet they are often distributed as flattened single-path or compound-path graphics, where the origina...

Agentic artificial intelligence (AI) in organizations is a sequential decision problem constrained by reliability and oversight cost. When deterministic workflo...

Recently, multimodal large language models (MLLMs) have emerged as a unified paradigm for language and image generation. Compared with diffusion models, MLLMs p...

General audio understanding is a fundamental goal for large audio-language models, with audio captioning serving as a cornerstone task for their development. Ho...

Generative world models offer a compelling foundation for augmented-reality (AR) applications: by predicting future image sequences that incorporate deliberate ...

Current audio deepfake detection has achieved remarkable performance using diverse deep learning architectures such as ResNet, and has seen further improvements...

Designing effective auxiliary rewards for cooperative multi-agent systems remains a precarious task; misaligned incentives risk inducing suboptimal coordination...

When multiple LLM-based code agents independently implement parts of the same class, they must agree on shared internal representations, even when the specifica...

Despite the advancements in cutting-edge technologies, audio signal processing continues to pose challenges and lacks the precision of a human speech processing...

Advances in diffusion-based video generation models, while significantly improving human animation, poses threats of misuse through the creation of fake videos ...

We introduce the Free-Market Algorithm (FMA), a novel metaheuristic inspired by free-market economics. Unlike Genetic Algorithms, Particle Swarm Optimization, a...

Video-language foundation models have proven to be highly effective in zero-shot applications across a wide range of tasks. A particularly challenging area is t...

Reliable evaluation of modern zero-shot text-to-speech (TTS) models remains challenging. Subjective tests are costly and hard to reproduce, while objective metr...

Diffusion-based video editing has emerged as an important paradigm for high-quality and flexible content generation. However, despite their generality and stron...

Probabilistic time series forecasting (PTSF) aims to model the full predictive distribution of future observations, enabling both accurate forecasting and princ...

Standard citation metrics treat all citations as equal, obscuring the social and structural pathways through which scholarly influence propagates. I introduce C...

Achieving natural full-duplex interaction in spoken dialogue systems (SDS) remains a challenge due to the difficulty of accurately detecting user interruptions....

Conversational artificial intelligence has the potential to assist users in preliminary medical consultations, particularly in settings where access to healthca...

Generative AI now produces photorealistic portraits that circulate widely in social and newslike contexts. Human ability to distinguish real from synthetic face...

While large language models have accelerated software development through "vibe coding", prototyping intelligent Extended Reality (XR) experiences remains inacc...

Accurate 3D reconstruction of deformable soft tissues is essential for surgical robotic perception. However, low-texture surfaces, specular highlights, and inst...

In this article, we focus on search algorithms for two-player perfect information games, whose objective is to determine the best possible strategy, and ideally...

The dense, temporal nature of video presents a profound challenge for automated analysis. Despite the use of powerful Vision-Language Models, prevailing methods...

Asynchronous messaging is a cornerstone of modern distributed systems, enabling decoupled communication for scalable and resilient applications. Today's message...

The computational demands of modern AI services are increasingly shifting execution beyond centralized clouds toward a computing continuum spanning edge and end...

Edge AI systems often operate under stringent energy and volume constraints that demand extreme efficiency under limited battery capacity, with requirements wor...

Deploying large language models on-device for always-on personal agents demands sustained inference from hardware tightly constrained in power, thermal envelope...

This paper presents ARYA, a composable, physics-constrained, deterministic world model architecture built on five foundational principles: nano models, composab...

Recent advancements and widespread adoption of Large Language Models (LLMs) in both industry and academia have catalyzed significant demand for LLM serving. How...

Federated Learning (FL) is constrained by the communication and energy limitations of decentralized edge devices. While gradient sparsification via Top-K magnit...

Vision-Language-Action (VLA) models are mainstream in embodied intelligence but face high inference costs. Edge-Cloud Collaborative (ECC) deployment offers an e...

Fully provisioned Message Passing Interface (MPI) parallelism achieves near-optimal wall-clock time for Computational Fluid Dynamics (CFD) solvers. This work ad...

Dynamic GNN inference has exhibited effectiveness in High Energy Physics (HEP) experiments at High Luminosity Large Hadron Collider (HL-LHC) due to strong capab...

Particle-in-Cell (PIC) Monte Carlo (MC) simulations are central to plasma physics but face increasing challenges on heterogeneous HPC systems due to excessive d...

The rapid deployment of machine learning across platforms from milliwatt-class TinyML devices to large language models has made energy efficiency a primary cons...

Distributed scientific workflows increasingly span heterogeneous compute clusters, edge resources, and geo-distributed data repositories. In these environments,...

Higher Degree by Research (HDR) candidates increasingly depend on cloud-provisioned virtual machines and local GPU hardware for their computational experiments,...

Peer-discovery protocols within P2P networks are often vulnerable: because creating network identities is essentially free, adversaries can eclipse honest nodes...

Multi-chain ecosystems suffer from fragmented identity, siloed liquidity, and bridge-dependent token transfers. We present n-VM, a Layer-1 architecture that hos...

Multimodal stacks that mix ViTs, CNNs, GNNs, and transformer NLP strain embedded platforms because their compute/memory patterns diverge and hard real-time targ...

Task-oriented object detection (TOOD) atop CLIP offers open-vocabulary, prompt-driven semantics, yet dense per-window computation and heavy memory traffic hinde...

Large-scale machine learning workloads increasingly rely on multi-GPU systems, yet their performance is often limited by an overlooked component: the CPU. Throu...

Large-scale distributed learning aims at minimizing a loss function $L$ that depends on a training dataset with respect to a $d$-length parameter vector. The di...

The growing demand for multi-DNN workloads with unpredictable task arrival times has highlighted the need for interruptible scheduling on edge accelerators. How...

Distributed prefix caching has become a core technique for efficient LLM serving. However, for long-context requests with high cache hit ratios, retrieving reus...

3D point cloud neural networks have significantly enhanced the perceptual capabilities of resource-limited mobile intelligent systems. However, despite the tran...

Effectively leveraging the vast computational resources of modern cloud environments requires expertise spanning multiple technical domains: configuring scienti...

The exponential growth in data has intensified the demand for computational power to train large-scale deep learning models. However, the rapid growth in model ...

Recent work distinguishes two heterophily regimes: adversarial, where cross-class edges dilute class signal and harm classification, and informative, where the ...

Safe navigation in complex environments remains a central challenge for reinforcement learning (RL) in robotics. This paper introduces Continuous Space-Time Emp...

This paper introduces Knowledge Graph based Massively Multi-task Model-based Policy Optimization (KG-M3PO), a framework for multi-task robotic manipulation in p...

Dynamism is common in AI computation, e.g., the dynamic tensor shapes and the dynamic control flows in models. Due to the long compilation time, existing runtim...

Despite deep learning's success in chemistry, its impact is hindered by a lack of interpretability and an inability to resolve activity cliffs, where minor stru...

Adaptive traffic signal control (ATSC) is crucial in alleviating congestion, maximizing throughput and promoting sustainable mobility in ever-expanding cities. ...

We propose a neuro-symbolic architecture that learns four interpretable physiological concepts, oculomotor dynamics, gaze stability, prefrontal hemodynamics, an...

A key challenge to understanding self-awareness has been a principled way of quantifying whether an intelligent system has a concept of a "self," and if so how ...

Cancer drug response varies widely across tumors due to multi-layer molecular heterogeneity, motivating computational decision support for precision oncology. D...

Accurate forecasting of multivariate time series remains challenging due to the need to capture both short-term fluctuations and long-range temporal dependencie...

WebAssembly's (Wasm) monolithic linear memory model facilitates memory corruption attacks that can escalate to cross-site scripting in browsers or go undetected...

RLHF-aligned language models exhibit response homogenization: on TruthfulQA (n=790), 40-79% of questions produce a single semantic cluster across 10 i.i.d. samp...

On-chip learning is key to scalable and adaptive neuromorphic systems, yet existing training methods are either difficult to implement in hardware or overly res...

The Industrial Internet of Things (IIoT) introduces significant security challenges as resource-constrained devices become increasingly integrated into critical...

Recently, reinforcement learning~(RL) has become an important approach for improving the capabilities of large language models~(LLMs). In particular, reinforcem...

The integration of GNSS data into portable devices has led to the generation of vast amounts of trajectory data, which is crucial for applications such as map-m...

This paper addresses the Service Network Design (SND) problem for a logistics service provider (LSP) operating in a multimodal freight transport network, consid...

We present an innovative, cost-effective framework integrating laboratory Hyperspectral Imaging (HSI) of the Bechar010 Lunar meteorite with ground-based lunar H...

Graph Neural Networks (GNNs) have achieved impressive performance in graph-related tasks. However, they suffer from poor generalization on out-of-distribution (...

Language-Assisted Image Clustering (LAIC) augments the input images with additional texts with the help of vision-language models (VLMs) to promote clustering p...

Nowadays, time series forecasting is predominantly approached through the end-to-end training of deep learning architectures using error-based objectives. While...

Machine learning models trained on small data sets for security applications are especially vulnerable to adversarial attacks. Person identification from LiDAR ...

In nonnegative matrix factorization (NMF), minimum-volume-constrained NMF is a widely used framework for identifying the solution of NMF by making basis vectors...

Recent advances in Large Language Models (LLMs) have inspired a surge of scaling law research in industrial search, advertising, and recommendation systems. How...

Reinforcement learning (RL) has emerged as a powerful paradigm for improving large language models beyond supervised fine-tuning, yet sustaining performance gai...