Guangtao Lyu

Orcid: 0009-0006-4474-2964

According to our database1, Guangtao Lyu authored at least 16 papers between 2022 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Revealing and Enhancing Core Visual Regions: Harnessing Internal Attention Dynamics for Hallucination Mitigation in LVLMs.
CoRR, February, 2026

Towards Interpretable Hallucination Analysis and Mitigation in LVLMs via Contrastive Neuron Steering.
CoRR, February, 2026

Beyond Global Alignment: Fine-Grained Motion-Language Retrieval via Pyramidal Shapley-Taylor Learning.
CoRR, January, 2026

Fisher-Driven Adaptive Locating for Knowledge Editing in Large Language Models.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

Semantically Comprehensive Token Pruning in LVLMs via Maximizing Concept Coverage.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

Channel-masked Asymmetric Distribution Matching for Cross-Domain Generalized Dataset Distillation.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
Towards Arbitrary Motion Completing via Hierarchical Continuous Representation.
CoRR, December, 2025

Revealing Perception and Generation Dynamics in LVLMs: Mitigating Hallucinations via Validated Dominance Correction.
CoRR, December, 2025

Tempo as the Stable Cue: Hierarchical Mixture of Tempo and Beat Experts for Music to 3D Dance Generation.
CoRR, December, 2025

Towards Unified Human Motion-Language Understanding via Sparse Interpretable Characterization.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024
LLM Knows Body Language, Too: Translating Speech Voices into Human Gestures.
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

2023
Corrigendum to "FETNet: Feature Erasing and Transferring Network for Scene Text Removal": Pattern Recognition Volume 140 (2023) 109531.
Pattern Recognit., September, 2023

FETNet: Feature erasing and transferring network for scene text removal.
Pattern Recognit., August, 2023

HelixNet: Dual Helix Cooperative Decoders for Scene Text Removal.
Proceedings of the Pattern Recognition and Computer Vision - 6th Chinese Conference, 2023

2022
MSLKANet: A Multi-Scale Large Kernel Attention Network for Scene Text Removal.
CoRR, 2022

PSSTRNet: Progressive Segmentation-Guided Scene Text Removal Network.
Proceedings of the IEEE International Conference on Multimedia and Expo, 2022


  Loading...