Xiaoyu Liu

papers

670

total citations

papers (11)

HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models

CVPR 2024arXiv

392

citations

CoA-VLA: Improving Vision-Language-Action Models via Visual-Text Chain-of-Affordance

ICCV 2025

citations

C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder

NEURIPS 2023arXiv

citations

Cross-Dimension Affinity Distillation for 3D EM Neuron Segmentation

CVPR 2024

citations

TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation

ICCV 2025arXiv

citations

Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composition

ICCV 2023arXiv

citations

Learning Cross-Representation Affinity Consistency for Sparsely Supervised Biomedical Instance Segmentation

ICCV 2023

citations

A Soma Segmentation Benchmark in Full Adult Fly Brain

CVPR 2023

citations

Xiaoyu Liu

papers (11)

HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models

VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

Spatially Adaptive Self-Supervised Learning for Real-World Image Denoising

Distilling Semantic Priors from SAM to Efficient Image Restoration Models

CoA-VLA: Improving Vision-Language-Action Models via Visual-Text Chain-of-Affordance

C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder

Cross-Dimension Affinity Distillation for 3D EM Neuron Segmentation

TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation

Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composition

Learning Cross-Representation Affinity Consistency for Sparsely Supervised Biomedical Instance Segmentation

A Soma Segmentation Benchmark in Full Adult Fly Brain

papers (11)

HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models

VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

Spatially Adaptive Self-Supervised Learning for Real-World Image Denoising

Distilling Semantic Priors from SAM to Efficient Image Restoration Models

CoA-VLA: Improving Vision-Language-Action Models via Visual-Text Chain-of-Affordance

C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder

Cross-Dimension Affinity Distillation for 3D EM Neuron Segmentation

TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation

Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composition

Learning Cross-Representation Affinity Consistency for Sparsely Supervised Biomedical Instance Segmentation

A Soma Segmentation Benchmark in Full Adult Fly Brain