8396 papers
This paper introduces Holi-Spatial, the first fully automated, large-scale, spatially-aware multimodal dataset constructed from raw video streams without human intervention, which provides 4 million high-quality 3D semantic annotations and spatial QA pairs to significantly enhance the training and performance of Vision-Language Models on spatial reasoning tasks.
This paper presents DAISS, a dual-arm robotic system that utilizes a phase-aware imitation learning policy trained on high-fidelity teleoperated demonstrations to automate the complex, asymmetric bimanual coordination required for ultrasound-guided needle interventions.
Ref-DGS is an efficient, rasterization-based framework that achieves state-of-the-art novel view synthesis on reflective scenes by decoupling surface geometry from specular reflections using a dual Gaussian representation and a lightweight adaptive mixing shader, thereby avoiding the high computational cost of explicit ray tracing.
This paper introduces FusionRegister, a general and efficient cross-modality registration framework guided by visual priors that directly corrects misalignment within fused infrared and visible images, thereby enhancing detail alignment and robustness without requiring extensive pre-registration.
This study investigates how varying levels of code obfuscation affect human program comprehension in Python and JavaScript, revealing that while obfuscation generally increases reasoning time and reduces accuracy, its impact is non-monotonic and language-specific, with moderate deliberation improving performance and experience proving more critical within specific languages than across them.
This survey provides a comprehensive overview of memory mechanisms in autonomous LLM agents from 2022 to early 2026, formalizing a write–manage–read framework, introducing a three-dimensional taxonomy, analyzing key mechanisms and evaluation benchmarks, and outlining critical applications and future challenges.
This paper presents an open-source, low-cost teleoperation framework for mobile bimanual manipulators that utilizes commodity hardware like smartphones and foot pedals to achieve intuitive whole-body control, demonstrating improved task performance and reduced cognitive load compared to traditional keyboard-based methods.
This paper introduces two novel model-driven evolutionary frameworks, NEMO-DE and NEEF-DE, that leverage differential evolution to perform near-field multi-source localization on continuous spherical-wave models with arbitrary array geometries, effectively overcoming the limitations of traditional grid-based subspace methods and data-dependent deep learning approaches without requiring labeled data or discretized grids.
UniUncer is a lightweight, unified framework for end-to-end autonomous driving that jointly estimates and leverages uncertainty for both static map elements and dynamic agents through probabilistic regression, uncertainty-aware query fusion, and adaptive gating, thereby significantly improving trajectory accuracy and planning robustness with minimal computational overhead.
FrameVGGT addresses the unbounded memory growth in streaming Visual Geometry Transformers by introducing a frame-driven rolling explicit-memory framework that aggregates frame-level evidence into compact prototypes, enabling stable long-sequence 3D perception under strict memory budgets.
This paper introduces RoboPCA, a pose-centered affordance learning framework that jointly predicts task-appropriate contact regions and poses from human demonstrations via the Human2Afford data curation pipeline, enabling robots to effectively manipulate objects with improved consistency and generalization across tasks and categories.
This paper proposes CDA-VSR, a compressed-domain-aware online video super-resolution network that leverages motion vectors, residual maps, and frame types to achieve real-time, high-quality reconstruction with significantly reduced computational cost compared to state-of-the-art methods.
This paper introduces the Masked Motion Diffusion Model (MMDM), a diffusion-based framework equipped with a Kinematic Attention Aggregation mechanism that learns context-adaptive motion priors to effectively reconstruct, refine, and complete 3D human motion from incomplete or noisy data.
C-Explorer is a decentralized framework for multi-UAV exploration that addresses communication limitations and inefficient traversal by utilizing connectivity-aware task representation and a contiguity-driven allocation strategy, achieving significant reductions in exploration time and path length compared to state-of-the-art methods.
TDM-R1 introduces a novel reinforcement learning paradigm that enables few-step diffusion models to effectively incorporate non-differentiable rewards by decoupling surrogate reward learning from generator training, achieving state-of-the-art performance across various metrics and scaling to powerful models like Z-Image with only 4 inference steps.
The paper introduces PARSE, a framework utilizing part-level geometric relations encoded in Part-centric Assembly Graphs to resolve spatial ambiguities, which is validated through the creation of the PARSE-10K dataset and demonstrated to significantly enhance both object layout reasoning in vision-language models and the physical realism of generated 3D scenes.
VoiceSHIELD-Small is a lightweight, real-time model built on Whisper-small that simultaneously transcribes speech and detects malicious content with 99.16% accuracy, offering a faster and more secure alternative to traditional text-based filtering for voice AI systems.
This paper presents YAQIN, a co-designed AI application that integrates Islamic frameworks and user-centered design to provide culturally sensitive mental health support for Muslim women in the UK, addressing gaps in trust and engagement through a faith-aware chatbot and guided journaling tool.
This Systematization of Knowledge (SoK) paper provides a comprehensive historical analysis of Maximal Extractable Value (MEV) by organizing fragmented literature into three chronological eras—from Miner Extractable Value in Proof-of-Work systems to the modern cross-chain frontier—while offering a unified taxonomy, identifying mitigations, and proposing a research agenda for standardized metrics and cross-chain infrastructure.
This paper demonstrates that large language models exhibit robust decision biases in two-arm bandit tasks, characterized by stubborn exploitation and low learning rates that persist across decoding parameters, thereby posing significant challenges for optimal human-AI collaboration.