Imagen de Portada

Repulsor: Accelerating Generative Modeling with a Contrastive Memory Bank

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Shaofeng, Chen, Xuanqi, Liao, Ning, Zhao, Haoxiang, Wang, Xiaoxing, Tan, Haoru, Wu, Sitong, Jia, Xiaosong, Fan, Qi, Yan, Junchi
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Dual-Branch Center-Surrounding Contrast: Rethinking Contrastive Learning for 3D Point Clouds
por: Zhang, Shaofeng, et al.
Publicado: (2025)

EvoTok: A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation
por: Li, Yan, et al.
Publicado: (2026)

FineRMoE: Dimension Expansion for Finer-Grained Expert with Its Upcycling Approach
por: Liao, Ning, et al.
Publicado: (2026)

Data Pruning by Information Maximization
por: Tan, Haoru, et al.
Publicado: (2025)

PointAlign: Feature-Level Alignment Regularization for 3D Vision-Language Models
por: Su, Yuanhao, et al.
Publicado: (2026)

Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling
por: Wu, Yihang, et al.
Publicado: (2026)

SWIFT: Prompt-Adaptive Memory for Efficient Interactive Long Video Generation
por: Tan, Shanwen, et al.
Publicado: (2026)

On the Evaluation and Refinement of Vision-Language Instruction Tuning Datasets
por: Liao, Ning, et al.
Publicado: (2023)

FlatFusion: Delving into Details of Sparse Transformer-based Camera-LiDAR Fusion for Autonomous Driving
por: Zhu, Yutao, et al.
Publicado: (2024)

PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
por: Zhang, Xiangdong, et al.
Publicado: (2024)

Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views
por: Zhang, Xiangdong, et al.
Publicado: (2025)

Can Users Specify Driving Speed? Bench2Drive-Speed: Benchmark and Baselines for Desired-Speed Conditioned Autonomous Driving
por: Shao, Yuqian, et al.
Publicado: (2026)

Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach
por: Zhang, Beichen, et al.
Publicado: (2024)

DreamWorld: Unified World Modeling in Video Generation
por: Tan, Boming, et al.
Publicado: (2026)

DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving
por: Jia, Xiaosong, et al.
Publicado: (2025)

Understanding Data Influence with Differential Approximation
por: Tan, Haoru, et al.
Publicado: (2025)

Exploiting Unlabeled Data with Multiple Expert Teachers for Open Vocabulary Aerial Object Detection and Its Orientation Adaptation
por: Li, Yan, et al.
Publicado: (2024)

VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models
por: Zhang, Xiangdong, et al.
Publicado: (2025)

Bench2Drive-R: Turning Real World Data into Reactive Closed-Loop Autonomous Driving Benchmark by Generative Model
por: You, Junqi, et al.
Publicado: (2024)

Grounding and Enhancing Grid-based Models for Neural Fields
por: Zhao, Zelin, et al.
Publicado: (2024)

ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving
por: Lu, Han, et al.
Publicado: (2024)

Ensemble Quadratic Assignment Network for Graph Matching
por: Tan, Haoru, et al.
Publicado: (2024)

Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving
por: Jia, Xiaosong, et al.
Publicado: (2024)

CrossEarth-SAR: A SAR-Centric and Billion-Scale Geospatial Foundation Model for Domain Generalizable Semantic Segmentation
por: Ye, Ziqi, et al.
Publicado: (2026)

AMP: Autoregressive Motion Prediction Revisited with Next Token Prediction for Autonomous Driving
por: Jia, Xiaosong, et al.
Publicado: (2024)

M-Tuning: Prompt Tuning with Mitigated Label Bias in Open-Set Scenarios
por: Liao, Ning, et al.
Publicado: (2023)

Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detection
por: Zhao, Shizhen, et al.
Publicado: (2025)

DreamOmni2: Multimodal Instruction-based Editing and Generation
por: Xia, Bin, et al.
Publicado: (2025)

Spatial Retrieval Augmented Autonomous Driving
por: Jia, Xiaosong, et al.
Publicado: (2025)

Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach
por: Zhang, Shaofeng, et al.
Publicado: (2024)

Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)
por: Yang, Zhenjie, et al.
Publicado: (2025)

LaGen: Towards Autoregressive LiDAR Scene Generation
por: Zhou, Sizhuo, et al.
Publicado: (2025)

DriveVGGT: Calibration-Constrained Visual Geometry Transformers for Multi-Camera Autonomous Driving
por: Jia, Xiaosong, et al.
Publicado: (2025)

Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention
por: Jia, Xiaosong, et al.
Publicado: (2026)

GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing
por: Liu, Mingxin, et al.
Publicado: (2026)

CIAR: Interval-based Collaborative Decoding for Image Generation Acceleration
por: Ye, Keming, et al.
Publicado: (2026)

Complementary and Contrastive Learning for Audio-Visual Segmentation
por: Gong, Sitong, et al.
Publicado: (2025)

Multimodal Task Representation Memory Bank vs. Catastrophic Forgetting in Anomaly Detection
por: Zhou, You, et al.
Publicado: (2025)

DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving
por: Yang, Zhenjie, et al.
Publicado: (2025)

GeoMix: Towards Geometry-Aware Data Augmentation
por: Zhao, Wentao, et al.
Publicado: (2024)