4506 papers
This paper introduces UniLongGen, a training-free inference strategy that improves long-horizon interleaved image generation by dynamically curating context to discard accumulated visual noise, thereby overcoming the reliability collapse caused by dense visual token interference in unified multimodal models.
The paper introduces CONSTANT, a novel one-shot handwriting generation framework that leverages Style-Aware Quantization and a latent patch-based contrastive objective within a diffusion model to overcome existing limitations in capturing diverse writer styles and generating high-quality, realistic handwritten images across multiple languages.
This paper evaluates the trade-off between privacy and Parkinson's disease detection in anonymized speech, demonstrating that while STT-TTS anonymization severely degrades diagnostic performance by erasing prosodic cues, kNN-VC effectively preserves macro-prosodic features to maintain high detection accuracy with only a minor performance drop.
This paper introduces a novel Speech Generation Speaker Poisoning (SGSP) framework to address privacy risks in zero-shot text-to-speech by modifying trained models to prevent the generation of specific speaker identities while maintaining utility for others, demonstrating effective protection for up to 15 speakers but revealing scalability challenges with larger sets due to identity overlap.
ReconDrive is a fast, feed-forward framework that adapts the VGGT foundation model with hybrid prediction heads and static-dynamic composition to achieve high-fidelity, scalable 4D Gaussian Splatting for autonomous driving scenes, outperforming existing feed-forward methods while matching the quality of slower optimization-based approaches.
This paper introduces a new deterministic symmetric recursive algorithm designed to solve mean-payoff games.
This paper introduces AgentRaft, an automated framework that combines program analysis and semantic reasoning to detect and quantify the systemic risk of Data Over-Exposure in LLM agents, demonstrating high accuracy and efficiency across thousands of real-world tools.
This paper proposes an active inference-based framework for micro-gesture recognition that utilizes Expected Free Energy-guided temporal sampling and uncertainty-aware adaptive learning to overcome challenges like low amplitude, noise, and inter-subject variability, demonstrating significant performance improvements on the SMG dataset.
This paper introduces StageFinder, a temporal graph learning framework that fuses host and network provenance data with graph neural networks and LSTMs to accurately and stably estimate Advanced Persistent Threat (APT) attack stages, achieving a macro F1-score of 0.96 on DARPA datasets.
PureCC is a novel concept customization framework that employs a decoupled learning objective and a dual-branch training pipeline to achieve high-fidelity text-to-image personalization while effectively preserving the original model's behavior and capabilities.
Brain-WM is a pioneering brain glioblastoma world model that utilizes a novel Y-shaped Mixture-of-Transformers architecture to unify next-step treatment prediction and future MRI generation, effectively capturing the co-evolutionary dynamics between tumor progression and treatment response to optimize clinical outcomes.
The paper proposes SiamGM, a real-time Siamese network for satellite video object tracking that integrates a geometry-aware Inter-Frame Graph Attention module and a motion-guided optimization strategy to effectively address challenges like small targets and occlusions while achieving 130 FPS without computational overhead.
This paper proposes an efficient multi-task RGB-D scene understanding model that integrates an enhanced fusion encoder, specialized feature interaction layers, and a dynamic adaptive loss function to simultaneously perform semantic, instance, and panoptic segmentation, orientation estimation, and scene classification with improved accuracy and speed across multiple datasets.
This paper proposes an Approximate Imitation Learning framework that enables a quadrotor to fly at high speeds through cluttered environments using only a single event camera by training an end-to-end neural network with a large offline dataset and lightweight state simulations, thereby avoiding the computational cost of rendering synthetic event data while achieving robust real-world performance.
FeasibleCap is a gripper-in-hand data collection system that provides real-time, hardware-free executability feedback through visual and haptic cues, enabling demonstrators to capture valid robot trajectories without headsets or learned dynamics models while improving replay success and preserving cross-embodiment transfer.
This paper introduces three neural-aided and model-based algorithms for dog dead reckoning (DDR) that utilize only inertial sensors to achieve accurate positioning with less than 10% absolute distance error for both biological and robotic dogs, validated through the newly created DogMotion dataset and a robotic legged dog dataset.
The paper introduces AiRWeb, a phone-based augmented reality system that allows users to seamlessly offload and organize arbitrary web content into their surrounding physical space to overcome mobile screen limitations, demonstrating its learnability and usability while highlighting design challenges in activation modes.
This paper proposes 3DGS-HPC, a novel framework that improves 3D Gaussian Splatting in real-world environments by replacing fragile semantic cues with a robust patch-wise classification strategy and a hybrid metric to effectively identify and suppress transient distractors like moving objects and shadows.
This paper presents deterministic polynomial-time algorithms and new structural bounds for factoring sparse polynomials with bounded individual degree, including recovering irreducible factors from blackbox access and improving upon previous runtime complexities for sparse polynomial factorization.
This paper proposes an efficient, end-to-end learned point cloud simplification method that combines feature embedding with attention-based sampling to achieve a superior balance between computational speed and accuracy for LiDAR-based object detection and classification compared to traditional sampling techniques.