Hongliang Li

papers

total citations

papers (12)

Bridging the Gap Between End-to-End and Two-Step Text Spotting

CVPR 2024arXiv

citations

DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding

CVPR 2025arXiv

citations

MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging

NEURIPS 2025arXiv

citations

Incrementer: Transformer for Class-Incremental Semantic Segmentation With Knowledge Distillation Focusing on Old Class

CVPR 2023

citations

Dual-Consistency Model Inversion for Non-Exemplar Class Incremental Learning

CVPR 2024

citations

CafeBoost: Causal Feature Boost To Eliminate Task-Induced Bias for Class Incremental Learning

CVPR 2023

citations

Contrastive Continuity on Augmentation Stability Rehearsal for Continual Self-Supervised Learning

ICCV 2023

citations

Class Incremental Learning with Multi-Teacher Distillation

CVPR 2024

citations

Hongliang Li

papers (12)

Bridging the Gap Between End-to-End and Two-Step Text Spotting

DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding

MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging

Prompt-Driven Referring Image Segmentation with Instance Contrasting

Offset Bin Classification Network for Accurate Object Detection

Learning with Noisy Class Labels for Instance Segmentation

CrossDet: Crossline Representation for Object Detection

Incrementer: Transformer for Class-Incremental Semantic Segmentation With Knowledge Distillation Focusing on Old Class

Dual-Consistency Model Inversion for Non-Exemplar Class Incremental Learning

CafeBoost: Causal Feature Boost To Eliminate Task-Induced Bias for Class Incremental Learning

Contrastive Continuity on Augmentation Stability Rehearsal for Continual Self-Supervised Learning

Class Incremental Learning with Multi-Teacher Distillation

papers (12)

Bridging the Gap Between End-to-End and Two-Step Text Spotting

DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding

MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging

Prompt-Driven Referring Image Segmentation with Instance Contrasting

Offset Bin Classification Network for Accurate Object Detection

Learning with Noisy Class Labels for Instance Segmentation

CrossDet: Crossline Representation for Object Detection

Incrementer: Transformer for Class-Incremental Semantic Segmentation With Knowledge Distillation Focusing on Old Class

Dual-Consistency Model Inversion for Non-Exemplar Class Incremental Learning

CafeBoost: Causal Feature Boost To Eliminate Task-Induced Bias for Class Incremental Learning

Contrastive Continuity on Augmentation Stability Rehearsal for Continual Self-Supervised Learning

Class Incremental Learning with Multi-Teacher Distillation