3447 papers
HECTOR is a novel video generation pipeline that enables fine-grained compositional control by supporting hybrid reference conditioning from static images and dynamic videos, while allowing users to explicitly specify the trajectories, locations, scales, and speeds of individual objects to synthesize coherent, high-fidelity videos.
This paper introduces deZent, a decentralized implementation of z-anonymity that utilizes stochastic counting structures and secure sums to coordinate privacy-preserving data anonymization across sensor networks, achieving performance comparable to centralized approaches while significantly reducing communication overhead and minimizing trust in a central entity.
This paper proposes an Adaptive SINDy framework that integrates data-driven Sparse Identification of Non-Linear Dynamics with Recursive Least Squares adaptive control to effectively identify residual forces and reject wind disturbances, demonstrating superior trajectory tracking performance compared to baseline PID and INDI controllers on a lightweight Crazyflie drone in turbulent environments.
This paper presents OptBench, an interactive workbench built on DuckDB that enables researchers and practitioners to transparently build, benchmark, and visually compare query optimizers for hybrid SQL and AI/ML workloads through a unified platform.
This study investigates cross-sensory correspondences between touch, smell, and emotion in 26 preschool-aged children (2–4 years) through playful tasks, revealing significant associations and underlying strategies that inform design guidelines and methods for understanding early childhood sensory cognition.
This paper employs fine-grained complexity to analyze the computational hardness of minimizing the Hausdorff distance under translation, revealing intricate dependencies on dimensionality, the directed versus undirected nature of the distance, and the choice between continuous and discrete translation spaces, including asymmetric time complexities and conditional lower bounds that distinguish these variants.
This paper proposes the H3LIX Decentralized Frontier Model Architecture, a distributed AI framework that enables privacy-preserving collective learning and sustainable scaling by aggregating locally generated synthetic reasoning signals into a shared Collective Context Field rather than relying on centralized model retraining.
This paper proposes preliminary design principles for GenAI-augmented Group Awareness Tools that leverage established mechanisms to foster autonomous socially shared metacognition in collaborative settings while mitigating the risk of over-reliance on AI-generated instructions.
This paper introduces a systematic framework for evaluating black-box patch attacks on three vision-language model-based autonomous driving architectures in CARLA simulation, revealing severe, sustained vulnerabilities and distinct failure patterns that highlight the inadequacy of current designs against physical adversarial threats.
This paper introduces Visual Query Segmentation (VQS), a new paradigm for pixel-level object localization in untrimmed videos, supported by the large-scale VQS-4K benchmark and the high-performing VQ-SAM method that extends SAM 2.
This paper proposes preliminary design principles for GenAI-augmented Group Awareness Tools that utilize implicit visualizations to trigger cognitive conflict and autonomous elaboration, thereby mitigating over-reliance on AI and fostering independent sensemaking in collaborative work and learning.
This paper introduces PSANE, a framework that enables legged robots to safely navigate and explore unknown deformable granular terrains by leveraging proprioceptive leg-terrain interactions to learn traversability models and optimize frontier selection for real-time, goal-directed navigation.
This paper presents an infrastructure-less magnetic localization system that enables a lightweight UAV to autonomously track and land with centimeter-level precision on a mobile quadruped robot by fusing real-time magneto-inductive sensing with inertial and optical-flow data, thereby enhancing heterogeneous robot collaboration in unknown environments without external anchors.
The MEGC 2026 challenge introduces two new tasks, Micro-Expression Video Question Answering (ME-VQA) and Micro-Expression Long-Video Question Answering (ME-LVQA), to advance the analysis of facial micro-expressions by leveraging the multimodal reasoning capabilities of large vision-language models on both short and long-duration video sequences.
TIDE is a training-free method that enables Diffusion Transformers to generate high-resolution images with arbitrary aspect ratios by introducing a text anchoring mechanism to correct prompt information loss and a step-aware dynamic temperature control to eliminate artifacts caused by attention dilution.
The paper introduces bsort, a non-comparison-based sorting algorithm that unifies the sorting of signed/unsigned integers and floating-point numbers with an asymptotic time complexity of and auxiliary space of , demonstrating competitive performance against optimized hybrid libraries for small word sizes.
This paper presents a one-pass random-order streaming algorithm that achieves an expected approximation factor of 0.7401 for the Unit Interval Selection problem using space linear in the optimal solution size, thereby improving upon the 2/3 bound established for adversarial streams while also providing matching space lower bounds for higher approximation factors.
This paper argues that while Generative AI offers potential assistance for qualitative research in software engineering, it is not a universal solution and requires careful, strategy-specific adaptation to avoid overgeneralization, ultimately outlining its promises, pitfalls, and implications for research quality.
The paper introduces FAME, a force-adaptive reinforcement learning framework that enables a full-scale humanoid to robustly maintain balance during bimanual manipulation by conditioning its policy on a learned latent context of joint configurations and estimated interaction forces, thereby significantly expanding its manipulation envelope without requiring wrist force sensors.
This paper examines the opportunities and challenges of integrating Virtual and Augmented Reality into public language education, finding that while these technologies boost motivation and contextual learning, their effective implementation requires overcoming technical barriers, cognitive overload, and curriculum alignment issues through improved design, infrastructure, and teacher training.