Stay updated with the latest research and technology news
arXiv:2508.04899v2 Announce Type: replace Abstract: Reliable evaluation of machine learning models for neonatal seizure detection is critical for clinical adoption. Current practices often rely on...
arXiv:2508.06249v2 Announce Type: replace Abstract: Fine-tuning lets practitioners repurpose aligned large language models (LLMs) for new domains, yet recent work reveals emergent misalignment (EMA): Even...
arXiv:2508.16332v3 Announce Type: replace Abstract: Controllable human voice generation, particularly for expressive domains like singing, remains a significant challenge. This paper introduces Vevo2, a unified...
arXiv:2508.16943v2 Announce Type: replace Abstract: We introduce LHM-Humanoid, a benchmark and learning framework for long-horizon whole-body humanoid loco-manipulation in diverse, cluttered scenes. In our setting,...
arXiv:2508.17488v3 Announce Type: replace Abstract: This paper tackles the critical challenge of optimizing multi-modality trackers by effectively adapting pre-trained models for RGB data. Existing fine-tuning...
arXiv:2508.18088v3 Announce Type: replace Abstract: This work presents a comprehensive evaluation of how quantization affects model bias, with particular attention to its impact on individual...
arXiv:2508.20315v2 Announce Type: replace Abstract: The growing complexity of urban mobility and the demand for efficient, sustainable, and adaptive solutions have positioned Intelligent Transportation Systems...
arXiv:2508.20643v2 Announce Type: replace Abstract: Post-mortem analysis of compromised systems is a key aspect of cyber forensics, today a mostly manual, slow, and error-prone task....
arXiv:2508.21279v2 Announce Type: replace Abstract: We present an energy conservative, quadrature based model reduction framework for the compressible Euler equations of Lagrangian hydrodynamics. Building on...
arXiv:2508.21592v4 Announce Type: replace Abstract: Traversing narrow gates presents a significant challenge and has become a standard benchmark for evaluating agile and precise quadrotor flight....
arXiv:2509.05609v2 Announce Type: replace Abstract: Aligning acoustic and linguistic representations is a central challenge to bridge the pre-trained models in knowledge transfer for automatic speech...
arXiv:2509.05983v4 Announce Type: replace Abstract: Code-switching (CS) presents a significant challenge for general Auto-Speech Recognition (ASR) systems. Existing methods often fail to capture the sub...
arXiv:2509.08177v2 Announce Type: replace Abstract: This paper presents a reinforcement learning-based quadrotor navigation method that leverages efficient differentiable simulation, novel loss functions, and privileged information...
arXiv:2509.10035v2 Announce Type: replace Abstract: Language use offers valuable insight into affective disorders such as bipolar disorder (BD), yet past research has been cross-sectional and...
arXiv:2509.10506v2 Announce Type: replace Abstract: Forecasting product demand in retail supply chains presents a complex challenge due to noisy, heterogeneous features and rapidly shifting consumer...
arXiv:2509.11612v2 Announce Type: replace Abstract: Reservoir is an efficient network for time series processing. It is well known that network structure is one of the...
arXiv:2509.11950v2 Announce Type: replace Abstract: Evaluating tabular generators remains a challenging problem, as the unique causal structural prior of heterogeneous tabular data does not lend...
arXiv:2509.12290v2 Announce Type: replace Abstract: Human oversight of AI is promoted as a safeguard against risks such as inaccurate outputs, system malfunctions, or violations of...
arXiv:2509.12890v2 Announce Type: replace Abstract: In Social Robot Navigation (SRN), the availability of meaningful metrics is crucial for evaluating trajectories from human-robot interactions. In the...
arXiv:2509.14882v2 Announce Type: replace Abstract: Speech Language Models (SpeechLMs) model tokenized speech to capture both semantic and acoustic information. When neural audio codecs based on...
arXiv:2509.15680v2 Announce Type: replace Abstract: We present SAM, a State-space Audio-language Model that integrates an audio encoder with a Mamba-2 backbone. SAM-2.7B achieves 21.1 mAP...
arXiv:2509.15877v2 Announce Type: replace Abstract: The star discrepancy is a quantitative measure of the uniformity of a point set in the unit cube. A central...
arXiv:2509.19696v3 Announce Type: replace Abstract: Learning-based methods excel at robot motion generation but remain limited in contact-rich physical interaction. Impedance control provides stable and safe...
arXiv:2509.19916v3 Announce Type: replace Abstract: Autonomous exploration in structured and complex indoor environments remains a challenging task, as existing methods often struggle to appropriately model...