Picture for Yuchen Yang

Yuchen Yang

Nankai University

Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation

Add code
Jun 24, 2024
Figure 1 for Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation
Figure 2 for Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation
Figure 3 for Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation
Figure 4 for Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation
Viaarxiv icon

Towards Holistic Language-video Representation: the language model-enhanced MSR-Video to Text Dataset

Add code
Jun 19, 2024
Viaarxiv icon

Monocular Localization with Semantics Map for Autonomous Vehicles

Add code
Jun 06, 2024
Viaarxiv icon

SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models

Add code
Apr 10, 2024
Figure 1 for SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models
Figure 2 for SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models
Figure 3 for SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models
Figure 4 for SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models
Viaarxiv icon

DictLLM: Harnessing Key-Value Data Structures with Large Language Models for Enhanced Medical Diagnostics

Add code
Feb 18, 2024
Viaarxiv icon

Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation

Add code
Dec 12, 2023
Figure 1 for Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation
Figure 2 for Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation
Figure 3 for Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation
Figure 4 for Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation
Viaarxiv icon

TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofing

Add code
Nov 30, 2023
Figure 1 for TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofing
Figure 2 for TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofing
Figure 3 for TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofing
Figure 4 for TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofing
Viaarxiv icon

Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learning

Add code
Oct 07, 2023
Figure 1 for Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learning
Figure 2 for Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learning
Figure 3 for Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learning
Figure 4 for Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learning
Viaarxiv icon

Robustness-Guided Image Synthesis for Data-Free Quantization

Add code
Oct 05, 2023
Figure 1 for Robustness-Guided Image Synthesis for Data-Free Quantization
Figure 2 for Robustness-Guided Image Synthesis for Data-Free Quantization
Figure 3 for Robustness-Guided Image Synthesis for Data-Free Quantization
Figure 4 for Robustness-Guided Image Synthesis for Data-Free Quantization
Viaarxiv icon

CLIPUNetr: Assisting Human-robot Interface for Uncalibrated Visual Servoing Control with CLIP-driven Referring Expression Segmentation

Add code
Sep 17, 2023
Figure 1 for CLIPUNetr: Assisting Human-robot Interface for Uncalibrated Visual Servoing Control with CLIP-driven Referring Expression Segmentation
Figure 2 for CLIPUNetr: Assisting Human-robot Interface for Uncalibrated Visual Servoing Control with CLIP-driven Referring Expression Segmentation
Figure 3 for CLIPUNetr: Assisting Human-robot Interface for Uncalibrated Visual Servoing Control with CLIP-driven Referring Expression Segmentation
Figure 4 for CLIPUNetr: Assisting Human-robot Interface for Uncalibrated Visual Servoing Control with CLIP-driven Referring Expression Segmentation
Viaarxiv icon