Canlyniadau Chwilio - Yu, Yizhou

OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels gan Lou, Meng, Yu, Yizhou

Cael y testun llawn
Cael y testun llawn

Decomposing Subject-Driven Image Generation via Intermediate Structural Prediction gan Guo, Hanzhong, Yu, Yizhou

Cael y testun llawn
Cael y testun llawn

Relationship-Embedded Representation Learning for Grounding Referring Expressions gan Yang, Sibei, Li, Guanbin, Yu, Yizhou

Cael y testun llawn
Cael y testun llawn

Graph-Structured Referring Expression Reasoning in The Wild gan Yang, Sibei, Li, Guanbin, Yu, Yizhou

Cael y testun llawn
Cael y testun llawn

ChestX-Det10: Chest X-ray Dataset on Detection of Thoracic Abnormalities gan Liu, Jingyu, Lian, Jie, Yu, Yizhou

Cael y testun llawn
Cael y testun llawn

Scene-Intuitive Agent for Remote Embodied Visual Grounding gan Lin, Xiangru, Li, Guanbin, Yu, Yizhou

Cael y testun llawn
Cael y testun llawn

GraphFPN: Graph Feature Pyramid Network for Object Detection gan Zhao, Gangming, Ge, Weifeng, Yu, Yizhou

Cael y testun llawn
Cael y testun llawn

I2F: A Unified Image-to-Feature Approach for Domain Adaptive Semantic Segmentation gan Ma, Haoyu, Lin, Xiangru, Yu, Yizhou

Cael y testun llawn
Cael y testun llawn

Adaptive Betweenness Clustering for Semi-Supervised Domain Adaptation gan Li, Jichang, Li, Guanbin, Yu, Yizhou

Cael y testun llawn
Cael y testun llawn

Inter-Domain Mixup for Semi-Supervised Domain Adaptation gan Li, Jichang, Li, Guanbin, Yu, Yizhou

Cael y testun llawn
Cael y testun llawn

LaMamba-Diff: Linear-Time High-Fidelity Diffusion Models Based on Local Attention and Mamba gan Fu, Yunxiang, Chen, Chaoqi, Yu, Yizhou

Cael y testun llawn
Cael y testun llawn

SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks gan Lou, Meng, Fu, Yunxiang, Yu, Yizhou

Cael y testun llawn
Cael y testun llawn

SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentation gan Fu, Yunxiang, Lou, Meng, Yu, Yizhou

Cael y testun llawn
Cael y testun llawn

A2Mamba: Attention-augmented State Space Models for Visual Recognition gan Lou, Meng, Fu, Yunxiang, Yu, Yizhou

Cael y testun llawn
Cael y testun llawn

Vision Function Layer in Multimodal LLMs gan Shi, Cheng, Yu, Yizhou, Yang, Sibei

Cael y testun llawn
Cael y testun llawn

Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-Experts gan Lou, Meng, Fu, Yunxiang, Yu, Yizhou

Cael y testun llawn
Cael y testun llawn

Parameters as Experts: Adapting Vision Models with Dynamic Parameter Routing gan Lou, Meng, Yu, Stanley, Yu, Yizhou

Cael y testun llawn
Cael y testun llawn

Vision Transformers Need More Than Registers gan Shi, Cheng, Yu, Yizhou, Yang, Sibei

Cael y testun llawn
Cael y testun llawn

Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysis gan Dai, Boyang, Chen, Chaoqi, Yu, Yizhou

Cael y testun llawn
Cael y testun llawn

Identifying Latent Concepts and Structures for Generalized Category Discovery gan Dai, Boyang, Chen, Chaoqi, Yu, Yizhou

Cael y testun llawn
Cael y testun llawn