Picture for Xin Dong

Xin Dong

Ray-Based Characterization of the AMPLE Model from 0.85 to 5 GHz

Add code
Apr 12, 2025
Viaarxiv icon

Development and Experimental Evaluation of a Vibration-Based Adhesion System for Miniature Wall-Climbing Robots

Add code
Apr 06, 2025
Viaarxiv icon

SMPR: A structure-enhanced multimodal drug-disease prediction model for drug repositioning and cold start

Add code
Mar 17, 2025
Viaarxiv icon

DOGR: Leveraging Document-Oriented Contrastive Learning in Generative Retrieval

Add code
Feb 12, 2025
Figure 1 for DOGR: Leveraging Document-Oriented Contrastive Learning in Generative Retrieval
Figure 2 for DOGR: Leveraging Document-Oriented Contrastive Learning in Generative Retrieval
Figure 3 for DOGR: Leveraging Document-Oriented Contrastive Learning in Generative Retrieval
Figure 4 for DOGR: Leveraging Document-Oriented Contrastive Learning in Generative Retrieval
Viaarxiv icon

Localization-Aware Multi-Scale Representation Learning for Repetitive Action Counting

Add code
Jan 13, 2025
Figure 1 for Localization-Aware Multi-Scale Representation Learning for Repetitive Action Counting
Figure 2 for Localization-Aware Multi-Scale Representation Learning for Repetitive Action Counting
Figure 3 for Localization-Aware Multi-Scale Representation Learning for Repetitive Action Counting
Figure 4 for Localization-Aware Multi-Scale Representation Learning for Repetitive Action Counting
Viaarxiv icon

DreamFit: Garment-Centric Human Generation via a Lightweight Anything-Dressing Encoder

Add code
Dec 23, 2024
Figure 1 for DreamFit: Garment-Centric Human Generation via a Lightweight Anything-Dressing Encoder
Figure 2 for DreamFit: Garment-Centric Human Generation via a Lightweight Anything-Dressing Encoder
Figure 3 for DreamFit: Garment-Centric Human Generation via a Lightweight Anything-Dressing Encoder
Figure 4 for DreamFit: Garment-Centric Human Generation via a Lightweight Anything-Dressing Encoder
Viaarxiv icon

AgentPS: Agentic Process Supervision for Multi-modal Content Quality Assurance through Multi-round QA

Add code
Dec 15, 2024
Figure 1 for AgentPS: Agentic Process Supervision for Multi-modal Content Quality Assurance through Multi-round QA
Figure 2 for AgentPS: Agentic Process Supervision for Multi-modal Content Quality Assurance through Multi-round QA
Figure 3 for AgentPS: Agentic Process Supervision for Multi-modal Content Quality Assurance through Multi-round QA
Figure 4 for AgentPS: Agentic Process Supervision for Multi-modal Content Quality Assurance through Multi-round QA
Viaarxiv icon

COEF-VQ: Cost-Efficient Video Quality Understanding through a Cascaded Multimodal LLM Framework

Add code
Dec 11, 2024
Viaarxiv icon

Hymba: A Hybrid-head Architecture for Small Language Models

Add code
Nov 20, 2024
Figure 1 for Hymba: A Hybrid-head Architecture for Small Language Models
Figure 2 for Hymba: A Hybrid-head Architecture for Small Language Models
Figure 3 for Hymba: A Hybrid-head Architecture for Small Language Models
Figure 4 for Hymba: A Hybrid-head Architecture for Small Language Models
Viaarxiv icon

Design, manufacturing, and inverse dynamic modeling of soft parallel robots actuated by dielectric elastomer actuators

Add code
Sep 30, 2024
Figure 1 for Design, manufacturing, and inverse dynamic modeling of soft parallel robots actuated by dielectric elastomer actuators
Figure 2 for Design, manufacturing, and inverse dynamic modeling of soft parallel robots actuated by dielectric elastomer actuators
Figure 3 for Design, manufacturing, and inverse dynamic modeling of soft parallel robots actuated by dielectric elastomer actuators
Figure 4 for Design, manufacturing, and inverse dynamic modeling of soft parallel robots actuated by dielectric elastomer actuators
Viaarxiv icon