8464 papers
The paper introduces FunnyNodules, a fully parameterized synthetic dataset of lung nodule-like shapes with controllable visual attributes and known decision rules, designed to systematically evaluate and benchmark explainable AI models by verifying whether they learn correct attribute-target relations and align their attention with relevant diagnostic features.
Bi-AQUA is a novel bilateral control-based imitation learning framework for underwater robot arms that integrates transformer-based action chunking with explicit lighting modeling to achieve robust performance in challenging, variable illumination conditions.
This paper introduces the Unified Attention-Mamba (UAM) backbone, a flexible architecture that seamlessly integrates Attention and Mamba modules without manual tuning, achieving state-of-the-art performance in both tumor cell classification and image segmentation tasks on public benchmarks.
EchoVLA is a memory-enhanced Vision-Language-Action model for mobile manipulation that synergizes scene and episodic declarative memories to improve navigation and task performance, validated by the new MoMani benchmark and demonstrating significant gains over existing baselines in both simulation and real-world settings.
SyncMV4D is a novel framework that overcomes the limitations of single-view and data-hungry 3D methods by introducing a Multi-view Joint Diffusion model and a Diffusion Points Aligner to simultaneously generate synchronized, realistic multi-view hand-object interaction videos and globally aligned 4D metric motions through a closed-loop coupling of visual appearance and dynamic geometry.
This paper proposes a novel autonomous lane-changing planning framework that integrates dynamic risk fields with time-varying convex feasible spaces and a constrained iLQR solver to achieve safe, efficient, and comfortable trajectories that outperform traditional methods in complex traffic scenarios.
This paper introduces ReInversion, a training-free exemplar-guided image editing method that employs a two-stage reversible denoising process and a Mask-Guided Selective Denoising strategy to achieve state-of-the-art performance with minimal computational overhead.
This paper presents a sex-stratified whole-body MR image registration method for the UK Biobank that leverages subcutaneous adipose tissue and muscle masks to significantly outperform existing intensity-based and deep learning approaches in anatomical alignment and correlation analysis accuracy.
This paper introduces UniTS, a unified spatio-temporal generative model based on flow matching and diffusion transformers that integrates tasks like cloud removal, change detection, and forecasting into a single framework, significantly outperforming specialized models under challenging conditions.
This paper introduces Safe Model Predictive Diffusion (Safe MPD), a training-free planning framework that integrates a safety shield directly into the diffusion denoising process to generate kinodynamically feasible and safe trajectories in real-time, outperforming existing methods in success rate and safety without requiring post-processing corrections.
Fast-BEV++ is a vision-only Bird's-Eye-View perception framework that resolves the trade-off between accuracy and deployment efficiency by employing a hardware-oriented, kernel-free architecture to achieve a new state-of-the-art 0.488 NDS on nuScenes while delivering real-time inference at over 134 FPS.
Photo3D is a framework that advances photorealistic 3D generation by leveraging GPT-4o-Image data within a structure-aligned multi-view synthesis pipeline to create detail-enhanced datasets, thereby enabling realistic texture refinement while preserving geometric consistency across diverse 3D-native generators.
This paper introduces a modular, fully learning-based neural image signal processing (ISP) framework that offers unprecedented control over intermediate rendering stages to enhance scalability, generalization, and flexibility, enabling a user-interactive photo-editing tool capable of unlimited post-editable re-rendering with competitive performance across multiple test sets.
UniCoR is a novel self-supervised framework that addresses the challenges of insufficient semantic understanding, inefficient modality fusion, and weak cross-language generalization in hybrid code retrieval by employing multi-perspective supervised contrastive learning and representation distribution consistency, thereby achieving state-of-the-art performance on both empirical and large-scale benchmarks.
This paper introduces VTP, a unified pre-training framework that optimizes visual tokenizers through joint image-text contrastive, self-supervised, and reconstruction losses to shift the latent space focus from low-level pixel accuracy to high-level semantics, thereby solving the "pre-training scaling problem" and enabling significantly improved, compute-efficient generative performance.
This paper argues that achieving high-performance end-to-end data movement requires shifting focus from raw network bandwidth to a holistic hardware-software co-design approach, introducing the "Drainage Basin Pattern" to identify and resolve bottlenecks across six critical paradigms ranging from network latency to host-side factors.
This paper introduces SORS, a modular, high-fidelity simulator based on the finite element method and constrained nonlinear optimization that accurately models complex soft robot dynamics and contact interactions, effectively bridging the sim-to-real gap for prototyping and control optimization.
This paper introduces a lightweight, pretrained history encoder that efficiently compresses long video histories into short embeddings using a frame query objective, enabling content-consistent autoregressive video generation under limited compute and memory constraints.
This paper introduces Spatial4D-Bench, a large-scale, multi-task benchmark comprising approximately 40,000 question-answer pairs across 18 tasks and six cognitive categories, designed to comprehensively evaluate and reveal the current limitations of Multimodal Large Language Models in achieving human-level 4D spatial intelligence.
This paper presents VISO, a robust underwater SLAM system that fuses stereo cameras, IMUs, and 3D sonar with novel calibration and photometric rendering techniques to achieve accurate 6-DoF localization and real-time, high-fidelity dense 3D reconstruction in challenging aquatic environments.