230 papers
This paper presents a hybrid learning and model-based approach that integrates multimodal tactile sensing with internal-force optimization to achieve reactive slip stabilization in multifingered grasps with a sub-50 ms closed-loop latency.
This paper extends the theory of Lorentzian and completely log-concave polynomials to proper convex cones by defining -Lorentzian forms and associated semipositive cones, establishing their geometric properties and negative-dependence interpretations, and applying these results to derive new Lyapunov stability criteria for cone-constrained evolution variational inequality systems.
This paper presents the design and experimental validation of a robust relative localization system for the SnailBot modular robot, which fuses ArUco marker recognition, optical flow, and IMU data to enable accurate real-time positioning for collaborative tasks.
LiM-YOLO is a streamlined ship detection model for optical remote sensing imagery that achieves state-of-the-art accuracy with fewer parameters by shifting the detection pyramid from P3-P5 to P2-P4 to better resolve small vessels and employing Group Normalization to stabilize training on high-resolution inputs.
This study demonstrates that in noisy dyadic conversations, speakers adapt by increasing hand-gesture complexity and speech volume while listeners enhance backchanneling, with background noise also modulating head and trunk movements and slightly reducing hand-speech synchrony.
This paper introduces Path-Consistent Safety Filtering (PACS), a novel approach that ensures formal safety guarantees for diffusion policies in dynamic environments while preserving task success rates by applying set-based reachability analysis to brake trajectories in a manner consistent with the policy's training distribution.
This paper investigates speech enhancement strategies within the latent space of neural audio codecs, demonstrating that predicting continuous latent representations with non-autoregressive models and fine-tuning the encoder yields the best overall performance, despite a trade-off in codec reconstruction quality.
This paper proposes a noise-conditioned mixture-of-experts framework for robust speaker verification that decomposes the feature space into specialized noise-aware subspaces using a routing mechanism, expert specialization strategy, and SNR-decaying curriculum learning to outperform conventional unified representation methods under diverse noisy conditions.
This paper proposes three content-aware MIMO-CC strategies (min-G, Grouping, and Phantom) for cache-aided asymmetric MIMO systems that dynamically optimize user selection and stream allocation to significantly enhance achievable degrees of freedom compared to existing approaches.
This paper introduces CoPeDiT, a unified 3D MRI synthesis framework that leverages a self-perceptive latent diffusion model with completeness-aware prompts to generate high-fidelity, structurally consistent images without relying on external manual guidance for missing data.
This paper presents the first systematic investigation into how accent information is encoded in Discrete Speech Representation Tokens (DSRTs), introducing a unified evaluation framework that reveals layer selection is the most critical factor for retaining accents, while ASR supervision significantly diminishes them and naive codebook reduction fails to disentangle accent from phonetic and speaker information.
This paper proposes a tiled beamspace MVDR architecture that achieves computationally efficient, high-performance wideband interference suppression for a 1024-element airborne radar by combining spatial and temporal dimensionality reduction with coordinated training across eight 128-element tiles.
This paper introduces a multiplexing paradigm for audio watermarking that combines multiple techniques, including the training-free Perceptual-Adaptive Time-Frequency Multiplexing (PA-TFM) and the model-based MaskNet, to significantly enhance robustness against sophisticated distortions and adversarial attacks compared to existing single-watermark schemes.
WhisperVC is a three-stage, low-resource framework that decouples cross-domain alignment from speech generation to effectively convert whispered speech into natural-sounding normal speech by leveraging domain-invariant semantic representations and speaker-conditioned timbre modeling.
This paper proposes a novel randomized space-time stacked intelligent metasurface (ST-SIM) architecture that integrates a time-varying input layer to exploit multiuser diversity and enable scalable massive downlink connectivity while significantly reducing channel state information acquisition and feedback overhead through a partial-CSIT-based beamforming scheme.
This paper proposes IMAS, a two-layer optimization algorithm that jointly selects sensing agents and synthesizes decentralized active perception policies in Dec-POMDPs by leveraging the submodularity of information-theoretic mutual information objectives to guarantee a -approximate performance.
This paper proposes a computationally efficient axial self-attention transformer neural receiver that reduces complexity from to while achieving state-of-the-art Block Error Rate performance under diverse 3GPP channel conditions.
This paper comprehensively evaluates 17 pretrained speech embedding systems across six heterogeneous datasets for dysarthria detection, revealing significant variability in within-dataset performance and limited cross-dataset generalization, which raises critical questions about the clinical validity of models trained and tested on the same data.
This paper introduces a systematic paradigm for benchmarking humans and machines on multilingual speech understanding tasks, revealing that while speech-based large language models match or exceed human performance in clean, single-speaker conditions, humans significantly outperform them in selectively attending to target speakers within complex, mixed-channel acoustic scenes, particularly in non-native languages.
This paper proposes a POMDP framework for minimizing long-term weighted distortion and transmission costs in remote tracking of Markov sources via multiple heterogeneous sensors with state-dependent accuracy, introducing truncation-based and discounted reformulation methods to solve the resulting infinite-state belief-MDP and demonstrating their superior performance and structural insights over low-complexity baselines.