8464 papers
SplitAgent introduces a novel distributed architecture that enables privacy-preserving collaboration between enterprise and cloud AI agents by utilizing context-aware dynamic sanitization, differential privacy, and zero-knowledge verification to achieve high task accuracy while significantly reducing data leakage compared to static approaches.
The paper proposes SAVE, a speech-aware video representation learning method that enhances video-text retrieval by introducing a dedicated speech branch and soft-ALBEF for early vision-audio alignment, achieving state-of-the-art performance across five benchmarks.
The paper introduces XTRIDE, a highly optimized n-gram-based approach that achieves state-of-the-art accuracy in recovering real-world structure layouts and function signatures from stripped binaries while offering throughput speeds 70 to 2300 times faster than existing methods, making it suitable for automated reverse engineering pipelines.
SRNeRV is a novel, parameter-efficient neural video representation framework that leverages scale self-similarity through a hybrid recursive sharing scheme to significantly reduce model size while achieving superior rate-distortion performance compared to traditional stacked multi-scale architectures.
GarmentPainter is an efficient framework that synthesizes high-fidelity, 3D-consistent garment textures in UV space by leveraging UV position maps for structural guidance and a type selection module for character-based control, all integrated into a standard diffusion model without architectural modifications.
This paper introduces a systematic framework for Large Audio-Language Models that reformulates ambiguous emotion recognition as a distributional reasoning problem, utilizing an ambiguity-aware objective and structured chain-of-thought supervision to significantly improve performance on standard benchmarks.
This paper presents a unified Lie-group framework based on Cosserat rod theory and SE(3) cumulative parameterization that overcomes existing modeling limitations to provide efficient, constraint-free analytical expressions for the kinematics, statics, and dynamics of diverse continuum soft robotic structures.
This study leverages the MICCAI 2024 UWF4DR dataset to benchmark state-of-the-art deep learning models, including CNNs, Vision Transformers, and foundation models, in both spatial and frequency domains for image quality assessment, referable diabetic retinopathy detection, and diabetic macular edema identification using ultra-widefield imaging, demonstrating that feature-level fusion and frequency-domain representations yield robust and explainable results.
This paper proposes a physics-guided preprocessing framework for millimeter-wave human pose estimation that explicitly models signal correlations and kinematics to achieve real-time, lightweight performance with significantly fewer parameters than existing data-driven baselines while maintaining competitive accuracy.
SiMO introduces a novel collaborative perception framework that utilizes Length-Adaptive Multi-Modal Fusion (LAMMA) and a "Pretrain-Align-Fuse-RD" training strategy to overcome sensor failures and semantic mismatches, ensuring robust performance across all individual modalities while maintaining effective multimodal integration.
This paper proposes a topologically stable variant of the Hough transform for line detection in point clouds, which replaces the traditional discretized voting scheme with a continuous score function and utilizes persistent homology to identify candidate lines via an efficient algorithm.
This paper proposes a novel flow-based conceptual design for coupling European capacity markets that, by harnessing cross-border capacity while respecting network constraints, reduces system costs and improves investment efficiency compared to isolated national mechanisms.
This paper introduces DynamicVGGT, a unified feed-forward framework that extends static 3D perception to dynamic 4D scene reconstruction for autonomous driving by jointly predicting current and future point maps, utilizing a Motion-aware Temporal Attention module for temporal coherence, and employing a Dynamic 3D Gaussian Splatting Head to explicitly model point motion and refine geometry.
The paper proposes WaDi, a novel one-step image synthesis framework that leverages the insight that weight direction changes are more critical than norm changes during distillation, introducing the parameter-efficient LoRaD adapter to achieve state-of-the-art performance with only 10% of trainable parameters.
Seed2Scale is a self-evolving data engine that overcomes data bottlenecks in embodied AI by synergizing a lightweight "SuperTiny" model for robust data collection with a large Vision-Language Model for autonomous quality verification, enabling a target model to achieve a 131.2% performance improvement starting from just four seed demonstrations.
The paper introduces FinToolBench, the first real-world, runnable benchmark that evaluates LLM agents on 760 executable financial tools using a novel framework assessing timeliness, intent, and regulatory compliance, alongside a proposed finance-aware baseline named FATR to advance trustworthy agentic AI in finance.
This paper proposes a learning-free method for 6D object pose tracking that fuses event-based optical flow for high-speed pose propagation with a template-based correction strategy, demonstrating superior performance over state-of-the-art algorithms in highly dynamic scenarios where traditional RGB-D cameras struggle with motion blur and low frame rates.
SAIL is a test-time scaling framework that enhances one-shot robot imitation learning by reframing trajectory generation as an iterative refinement process guided by Monte Carlo Tree Search, an automated retrieval archive, and a vision-language model-based scoring mechanism, thereby significantly improving success rates across diverse manipulation tasks.
This paper introduces a prototype-guided approach that leverages the intrinsic embedding geometry of diffusion models to identify and cluster concept representations, enabling the reliable erasure of broad, multi-faceted concepts while preserving overall image quality.
This paper demonstrates that explicitly reducing observation dimensionality and implementing locality-aware credit assignment in a communication-free multi-agent system enhances robustness and performance in asymmetric 3D pursuit-evasion tasks within cluttered environments.