Picture for Yan Li

Yan Li

University of Minnesota

Self-Paced Learning Strategy with Easy Sample Prior Based on Confidence for the Flying Bird Object Detection Model Training

Add code
Dec 09, 2024
Viaarxiv icon

SINGER: Vivid Audio-driven Singing Video Generation with Multi-scale Spectral Diffusion Model

Add code
Dec 04, 2024
Viaarxiv icon

COMET:Combined Matrix for Elucidating Targets

Add code
Dec 03, 2024
Viaarxiv icon

AlignMamba: Enhancing Multimodal Mamba with Local and Global Cross-modal Alignment

Add code
Dec 01, 2024
Viaarxiv icon

Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy

Add code
Nov 23, 2024
Figure 1 for Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy
Figure 2 for Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy
Figure 3 for Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy
Figure 4 for Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy
Viaarxiv icon

Exploiting Unlabeled Data with Multiple Expert Teachers for Open Vocabulary Aerial Object Detection and Its Orientation Adaptation

Add code
Nov 04, 2024
Figure 1 for Exploiting Unlabeled Data with Multiple Expert Teachers for Open Vocabulary Aerial Object Detection and Its Orientation Adaptation
Figure 2 for Exploiting Unlabeled Data with Multiple Expert Teachers for Open Vocabulary Aerial Object Detection and Its Orientation Adaptation
Figure 3 for Exploiting Unlabeled Data with Multiple Expert Teachers for Open Vocabulary Aerial Object Detection and Its Orientation Adaptation
Figure 4 for Exploiting Unlabeled Data with Multiple Expert Teachers for Open Vocabulary Aerial Object Detection and Its Orientation Adaptation
Viaarxiv icon

A Unified Solution to Diverse Heterogeneities in One-shot Federated Learning

Add code
Oct 28, 2024
Figure 1 for A Unified Solution to Diverse Heterogeneities in One-shot Federated Learning
Figure 2 for A Unified Solution to Diverse Heterogeneities in One-shot Federated Learning
Figure 3 for A Unified Solution to Diverse Heterogeneities in One-shot Federated Learning
Figure 4 for A Unified Solution to Diverse Heterogeneities in One-shot Federated Learning
Viaarxiv icon

Efficient Diversity-based Experience Replay for Deep Reinforcement Learning

Add code
Oct 27, 2024
Viaarxiv icon

ChuLo: Chunk-Level Key Information Representation for Long Document Processing

Add code
Oct 14, 2024
Figure 1 for ChuLo: Chunk-Level Key Information Representation for Long Document Processing
Figure 2 for ChuLo: Chunk-Level Key Information Representation for Long Document Processing
Figure 3 for ChuLo: Chunk-Level Key Information Representation for Long Document Processing
Figure 4 for ChuLo: Chunk-Level Key Information Representation for Long Document Processing
Viaarxiv icon

Unity is Power: Semi-Asynchronous Collaborative Training of Large-Scale Models with Structured Pruning in Resource-Limited Clients

Add code
Oct 11, 2024
Figure 1 for Unity is Power: Semi-Asynchronous Collaborative Training of Large-Scale Models with Structured Pruning in Resource-Limited Clients
Figure 2 for Unity is Power: Semi-Asynchronous Collaborative Training of Large-Scale Models with Structured Pruning in Resource-Limited Clients
Figure 3 for Unity is Power: Semi-Asynchronous Collaborative Training of Large-Scale Models with Structured Pruning in Resource-Limited Clients
Figure 4 for Unity is Power: Semi-Asynchronous Collaborative Training of Large-Scale Models with Structured Pruning in Resource-Limited Clients
Viaarxiv icon