Stay updated with the latest research and technology news
arXiv:2601.22660v1 Announce Type: new Abstract: We investigate progressive freezing as an alternative to straight-through estimators (STE) for training binary networks from scratch. Under controlled training...
arXiv:2601.22661v1 Announce Type: new Abstract: Recent advances in Large Audio Language Models (LALMs) have extended Text-to-Speech (TTS) to interactive role-play scenarios, which demand high expressiveness...
arXiv:2601.22662v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong capabilities across diverse decision-making tasks. However, existing approaches often overlook the specialization differences...
arXiv:2601.22663v1 Announce Type: new Abstract: As the quality of synthetic images improves, identifying the underlying concepts of model-generated images is becoming increasingly crucial for copyright...
arXiv:2601.22664v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for aligning large language models (LLMs) with human preferences, yet...
arXiv:2601.22666v1 Announce Type: new Abstract: Open-vocabulary grounding requires accurate vision-language alignment under weak supervision, yet existing methods either rely on global sentence embeddings that lack...
arXiv:2601.22667v1 Announce Type: new Abstract: This paper examines the organizational implications of Generative AI adoption in software engineering through a multiple-case comparative study. We contrast...
arXiv:2601.22669v1 Announce Type: new Abstract: Federated Learning (FL) facilitates decentralized collaborative learning without transmitting raw data. However, reliance on fixed global rounds or validation data...
arXiv:2601.22672v1 Announce Type: new Abstract: Conjoined collaborative robots, functioning as supernumerary robotic bodies (SRBs), can enhance human load tolerance abilities. However, in tasks involving physical...
arXiv:2601.22674v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) suffer from high computational costs due to excessive visual tokens, particularly in high-resolution and video-based...
arXiv:2601.22675v1 Announce Type: new Abstract: Spiking neural networks (SNNs) have gained traction in vision due to their energy efficiency, bio-plausibility, and inherent temporal processing. Yet,...
arXiv:2601.22676v1 Announce Type: new Abstract: Logs serve as a primary source of information for engineers to diagnose failures in large-scale online service systems. Log parsing,...
arXiv:2601.22678v1 Announce Type: new Abstract: Full-graph and mini-batch Graph Neural Network (GNN) training approaches have distinct system design demands, making it crucial to choose the...
arXiv:2601.22679v1 Announce Type: new Abstract: Consistency models have been proposed for fast generative modeling, achieving results competitive with diffusion and flow models. However, these methods...
arXiv:2601.22680v1 Announce Type: new Abstract: We introduce the Visual Personalization Turing Test (VPTT), a new paradigm for evaluating contextual visual personalization based on perceptual indistinguishability,...
arXiv:2601.22685v1 Announce Type: new Abstract: Zero-shot out-of-vocabulary detection (ZS-OOVD) aims to accurately recognize objects of in-vocabulary (IV) categories provided at zero-shot inference, while simultaneously rejecting...
arXiv:2601.22686v1 Announce Type: new Abstract: Aerial manipulators (AMs) are gaining increasing attention in automated transportation and emergency services due to their superior dexterity compared to...
arXiv:2601.22687v1 Announce Type: new Abstract: The Swift--Hohenberg equation is a widely studied fourth-order model, originally proposed to describe hydrodynamic fluctuations. It admits an energy-dissipation law...
arXiv:2601.22688v1 Announce Type: new Abstract: Language models generate reasoning sequentially, preventing them from decoupling irrelevant exploration paths during search. We introduce Tree-Structured Language Modeling (TSLM),...
arXiv:2601.22689v1 Announce Type: new Abstract: Robots are becoming more prominent in assisting persons with disabilities (PwD). Whilst there is broad consensus that robots can assist...
arXiv:2601.22690v1 Announce Type: new Abstract: Large language models (LLMs) based on the Transformer have demonstrated strong performance across diverse tasks. However, current models still exhibit...
arXiv:2601.22691v1 Announce Type: new Abstract: Feder-Vardi conjecture, which proposed that every finite-domain Constraint Satisfaction Problem (CSP) is either in P or it is NP-complete, has...
arXiv:2601.22692v1 Announce Type: new Abstract: The development of large language models (LLMs) is costly and has significant commercial value. Consequently, preventing unauthorized appropriation of open-source...
arXiv:2601.22693v1 Announce Type: new Abstract: Reconstructing detailed 3D human meshes from a single in-the-wild image remains a fundamental challenge in computer vision. Existing SMPLX-based methods...