2528 papers
CogBlender is a novel framework that enables continuous, multi-dimensional control over the cognitive properties of text-to-image generation by mapping cognitive space to visual semantics and dynamically steering the flow-matching process through interpolated velocity fields guided by cognitive anchors.
The paper introduces MDTrack, a novel multimodal object tracking framework that achieves state-of-the-art performance by employing a Mixture of Experts for adaptive modality-aware fusion and utilizing decoupled State Space Models with cross-attention mechanisms for independent yet synergistic temporal propagation.
ToolRosetta is a unified framework that automatically transforms heterogeneous open-source code repositories into standardized, secure, and executable Model Context Protocol (MCP) tools, enabling LLM agents to autonomously plan and invoke specialized software for complex tasks with minimal human intervention.
The paper introduces See, Plan, Rewind (SPR), a progress-aware vision-language-action framework that enhances robotic manipulation robustness by dynamically grounding instructions into spatial subgoals and enabling closed-loop error recovery through state rewinding, achieving state-of-the-art performance on challenging benchmarks without additional training.
This study systematically investigates how network latency degrades the pragmatic and hedonic dimensions of Quality of Experience in networked VR whiteboards by analyzing their varying impacts across sequential and free collaboration modes, as well as between avatar-enhanced and traditional VR or PC-based systems.
CORAL is a scalable, embodiment-agnostic framework that mitigates multi-task interference and catastrophic forgetting in Vision-Language-Action models by freezing a shared backbone and dynamically routing language instructions to task-specific, lightweight LoRA experts with zero inference overhead.
This paper proposes a paralinguistic- and emotion-aware model that detects optimal timing for emotional validation in Japanese empathetic dialogue using only speech signals, achieving significant improvements over conventional baselines by integrating self-supervised paralinguistic and multi-task emotion classification encoders.
This paper proposes and validates an open-source RISC-V-based Trusted Execution Environment that acts as an external entropy service, enabling constrained IoT devices to securely obtain high-quality random numbers for cryptographic key generation by leveraging initial trust and potentially expanding with additional sensor-based entropy sources.
The paper introduces IntroSVG, an introspective framework that enhances text-to-SVG generation by employing a unified Visual Language Model in a closed-loop "generate-review-refine" cycle, where the model acts as both generator and critic to iteratively improve outputs based on visual rendering feedback.
The paper presents NLiPsCalib, an efficient and physics-consistent calibration framework that utilizes Near-Light Photometric Stereo and controllable light sources to enable high-fidelity 3D reconstruction of curved visuotactile sensors through simple contacts with everyday objects, thereby overcoming the cost and complexity of existing methods.
This paper introduces OddGridBench, a benchmark revealing that current multimodal large language models significantly underperform humans in detecting fine-grained visual discrepancies, and proposes OddGrid-GRPO, a reinforcement learning framework that effectively enhances this sensitivity through curriculum learning and distance-aware rewards.
This paper presents a honeypot-based study conducted in early 2025 that reveals human Tor users primarily discover onion sites via the Ahmia search engine and exhibit significantly higher engagement with child sexual abuse material (CSAM) compared to other illicit categories, with English-language versions attracting the most interaction.
This paper presents a Dynamic Precision Math Engine for ESP32 microcontrollers that integrates Q16.16 fixed-point arithmetic, a CORDIC trigonometric module, and a cache-aware matrix kernel to achieve significant speedups in linear algebra and trigonometry through a runtime-switchable architecture that balances integer efficiency with floating-point precision.
This case study demonstrates that while ChatGPT can generate realistic synthetic system requirement specifications across multiple industries using iterative prompt engineering, the resulting artifacts still contain significant flaws that necessitate thorough expert evaluation rather than relying solely on LLM-based quality assessments.
This paper proposes Predictive Spectral Calibration (PSC), a simple and model-agnostic source-free framework that enhances test-time adaptation for image regression by extending subspace alignment to block spectral matching, thereby achieving consistent performance improvements over strong baselines, especially under severe distribution shifts.
This ICDE 2026 tutorial paper provides a comprehensive overview of the synergistic "virtuous cycle" between AI and vector search, detailing how AI enhances vector search efficiency and how vector search, particularly through Retrieval-Augmented Generation, empowers Large Language Models, while also exploring co-optimization strategies, challenges, and future research directions.
This paper proposes a robust and provably secure image steganography framework that utilizes latent-space iterative optimization to significantly enhance message extraction accuracy under various compression and processing scenarios while maintaining security guarantees.
ProvAgent is a novel framework that enhances threat detection and investigation by integrating graph contrastive learning for high-fidelity alert generation with a multi-agent collaborative system to autonomously reconstruct complex APT attack processes, thereby overcoming the limitations of traditional human-model collaboration.
This paper introduces Evidential Perfusion Physics-Informed Neural Networks (EPPINN), a novel framework that integrates evidential deep learning with physics-informed modeling to quantify both aleatoric and epistemic uncertainties in CT perfusion imaging, thereby achieving superior accuracy and reliability in acute ischemic stroke assessment compared to existing deterministic methods.
SinGeo is a novel framework that achieves robust cross-view geo-localization using a single model by employing a dual discriminative learning architecture and a curriculum learning strategy, thereby overcoming the limitations of existing methods that struggle with unseen fields of view and orientations.