4012 papers
This paper introduces Poly2Graph, an automated pipeline for generating HSG-12M, a pioneering 16.7-million-scale dataset of spatial multigraphs derived from non-Hermitian crystal energy spectra, which bridges condensed matter physics and geometry-aware graph learning by preserving vital geometric information often discarded in existing benchmarks.
InterActHuman is a novel framework that enables high-quality multi-concept human animation by enforcing strong, region-specific binding of text, image, and audio conditions to individual identities, thereby overcoming the limitations of global-conditioning methods in scenarios involving complex human-human and human-object interactions.
AutoV is a lightweight, annotation-free framework that enhances Large Vision-Language Models by automatically retrieving instance-adaptive visual prompts based on loss-oriented ranking, thereby overcoming the performance saturation of single-prompt designs and significantly improving performance across various visual understanding tasks.
This paper introduces TreeBench, a diagnostic benchmark for evaluating traceable visual grounded reasoning, and proposes TreeVGR, a reinforcement learning-based training paradigm that significantly enhances model performance by jointly supervising localization and reasoning.
The paper introduces GMLN-BTS, a lightweight graph-based multi-modal network that achieves state-of-the-art brain tumor segmentation with high precision and minimal computational cost (4.58M parameters) by integrating a modality-aware encoder, a graph-based collaborative interaction module, and a voxel refinement upsampling mechanism.
This paper proposes EDA, a unified theoretical framework that extends diffusion models to handle arbitrary noise patterns without increasing computational overhead, thereby significantly improving performance and generalization in diverse image restoration tasks such as medical imaging and natural scene recovery.
SAMPO-Path introduces a novel preference optimization framework that aligns pathology foundation models with clinical segmentation intents by adapting Direct Preference Optimization to vision tasks, thereby significantly improving segmentation accuracy and robustness against noisy prompts in dense histopathology images.
This paper proposes a novel significance-regularized fine-tuning framework that optimizes multi-modality trackers by dynamically balancing parameter significance for generalization and adaptability, thereby achieving superior performance across various benchmarks compared to state-of-the-art methods.
This paper presents a reinforcement learning-based quadrotor navigation method that utilizes privileged time-of-arrival maps and a yaw alignment loss to successfully navigate around large obstacles in cluttered environments, achieving an 86% success rate in simulation and demonstrating collision-free flight in real-world outdoor conditions.
This paper proposes a reliable, computation-efficient system for 3D localisation of distant objects in safety-critical surveillance tasks like wildfire monitoring by applying multi-view triangulation or particle filters to noisy image segmentation sequences from drones, offering shape and uncertainty estimates without requiring specialised sensors or full 3D reconstruction.
BridgeDrive introduces a novel anchor-guided diffusion bridge policy that ensures theoretical consistency between forward and reverse processes to transform coarse expert trajectories into refined, safe, and reactive closed-loop plans, achieving state-of-the-art performance on the Bench2Drive benchmark.
The paper proposes SphereAR, a hyperspherical latent-based autoregressive model that constrains inputs and outputs to a fixed-radius hypersphere to eliminate variance collapse and achieve state-of-the-art image generation performance, surpassing diffusion and masked-generation models at comparable scales.
This paper introduces Continuous Space-Time Video Super-Resolution using 3D Video Fourier Fields (VFF), a novel neural approach that encodes video as a continuous spatio-temporal representation to achieve superior spatial sharpness, temporal consistency, and computational efficiency compared to existing methods.
This paper introduces EgoTraj-Bench, the first real-world benchmark for ego-centric trajectory prediction under noisy observations, and proposes BiFlow, a dual-stream flow matching model with an EgoAnchor mechanism that achieves state-of-the-art robustness by concurrently denoising historical inputs and forecasting future motion.
This paper proposes SpecMCD, a weakly supervised cloud detection method that combines spectral features with a multi-scale scene-level deep network and a progressive training framework to generate highly accurate pixel-level cloud masks, achieving significant performance improvements over existing methods on Gaofen-1 multispectral images.
VidGuard-R1 is a novel AI-generated video detector that leverages Group Relative Policy Optimization (GRPO) and specialized reward models to overcome the limitations of static datasets, achieving state-of-the-art zero-shot performance while providing human-interpretable, physics-grounded explanations for its forensic judgments.
This paper introduces SpineMed, a clinician-co-designed ecosystem featuring the 450k-instance SpineMed-450k dataset and the SpineBench evaluation framework, which together enable and validate significant improvements in level-aware, multimodal reasoning for spine disorder diagnosis and surgical planning.
ExposureEngine is an end-to-end system that addresses the limitations of traditional horizontal bounding box methods by utilizing oriented bounding boxes and a language-driven agentic layer to provide accurate, rotation-aware sponsor visibility analytics and automated reporting for sports broadcasts.
The paper introduces TerraCodec, a family of publicly available, pretrained neural codecs for Earth observation data that utilizes a Temporal Transformer and a novel Latent Repacking method to achieve significantly higher compression rates than classical codecs while enabling zero-shot cloud inpainting.
This paper introduces XFactor, the first geometry-free self-supervised model that achieves true novel view synthesis by disentangling camera pose from scene content through a novel augmentation scheme, thereby enabling pose transferability across different 3D scenes without relying on explicit 3D inductive biases.