Xin Geng

papers

750

total citations

papers (23)

One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancement

NEURIPS 2022arXiv

citations

Improved Noise Schedule for Diffusion Training

ICCV 2025arXiv

citations

Towards Effective Visual Representations for Partial-Label Learning

CVPR 2023arXiv

citations

Transformer as Linear Expansion of Learngene

AAAI 2024arXiv

citations

Learning From Biased Soft Labels

NEURIPS 2023arXiv

citations

WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models

CVPR 2025arXiv

citations

Mimic In-Context Learning for Multimodal Tasks

CVPR 2025arXiv

citations

Building Variable-Sized Models via Learngene Pool

AAAI 2024arXiv

citations

Selective Label Enhancement Learning for Test-Time Adaptation

ICLR 2025

citations

Progressively Label Enhancement for Large Language Model Alignment

ICML 2025arXiv

citations

One-Shot Knowledge Transfer for Scalable Person Re-Identification

ICCV 2025arXiv

citations

Aligned Objective for Soft-Pseudo-Label Generation in Supervised Learning

ICML 2024

citations

Label Distribution Learning on Auxiliary Label Space Graphs for Facial Expression Recognition

CVPR 2020

citations

Inheriting Generalized Learngene for Efficient Knowledge Transfer across Multiple Tasks

AAAI 2025

citations

Correlation-Induced Label Prior for Semi-Supervised Multi-Label Learning

ICML 2024

citations

ULAREF: A Unified Label Refinement Framework for Learning with Inaccurate Supervision

ICML 2024

citations

Learning with Partial-Label and Unlabeled Data: A Uniform Treatment for Supervision Redundancy and Insufficiency

ICML 2024

citations

Vision Transformers as Probabilistic Expansion from Learngene

ICML 2024

citations

Redefining <Creative> in Dictionary: Towards an Enhanced Semantic Understanding of Creative Generation

CVPR 2025arXiv

citations

Xin Geng

papers (23)

Efficient Diffusion Training via Min-SNR Weighting Strategy

Provably Consistent Partial-Label Learning

Instance-Dependent Partial Label Learning

Exploring Diverse In-Context Configurations for Image Captioning

One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancement

Improved Noise Schedule for Diffusion Training

Towards Effective Visual Representations for Partial-Label Learning

Transformer as Linear Expansion of Learngene

Learning From Biased Soft Labels

WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models

Mimic In-Context Learning for Multimodal Tasks

Building Variable-Sized Models via Learngene Pool

Selective Label Enhancement Learning for Test-Time Adaptation

Progressively Label Enhancement for Large Language Model Alignment

One-Shot Knowledge Transfer for Scalable Person Re-Identification

Aligned Objective for Soft-Pseudo-Label Generation in Supervised Learning

Label Distribution Learning on Auxiliary Label Space Graphs for Facial Expression Recognition

Inheriting Generalized Learngene for Efficient Knowledge Transfer across Multiple Tasks

Correlation-Induced Label Prior for Semi-Supervised Multi-Label Learning

ULAREF: A Unified Label Refinement Framework for Learning with Inaccurate Supervision

Learning with Partial-Label and Unlabeled Data: A Uniform Treatment for Supervision Redundancy and Insufficiency

Vision Transformers as Probabilistic Expansion from Learngene

Redefining <Creative> in Dictionary: Towards an Enhanced Semantic Understanding of Creative Generation

papers (23)

Efficient Diffusion Training via Min-SNR Weighting Strategy

Provably Consistent Partial-Label Learning

Instance-Dependent Partial Label Learning

Exploring Diverse In-Context Configurations for Image Captioning

One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancement

Improved Noise Schedule for Diffusion Training

Towards Effective Visual Representations for Partial-Label Learning

Transformer as Linear Expansion of Learngene

Learning From Biased Soft Labels

WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models

Mimic In-Context Learning for Multimodal Tasks

Building Variable-Sized Models via Learngene Pool

Selective Label Enhancement Learning for Test-Time Adaptation

Progressively Label Enhancement for Large Language Model Alignment

One-Shot Knowledge Transfer for Scalable Person Re-Identification

Aligned Objective for Soft-Pseudo-Label Generation in Supervised Learning

Label Distribution Learning on Auxiliary Label Space Graphs for Facial Expression Recognition

Inheriting Generalized Learngene for Efficient Knowledge Transfer across Multiple Tasks

Correlation-Induced Label Prior for Semi-Supervised Multi-Label Learning

ULAREF: A Unified Label Refinement Framework for Learning with Inaccurate Supervision

Learning with Partial-Label and Unlabeled Data: A Uniform Treatment for Supervision Redundancy and Insufficiency

Vision Transformers as Probabilistic Expansion from Learngene

Redefining <Creative> in Dictionary: Towards an Enhanced Semantic Understanding of Creative Generation