Cheng Shi

papers

373

total citations

papers (12)

Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator

NEURIPS 2023arXiv

101

citations

LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models

ICCV 2023arXiv

citations

Spatial and Visual Perspective-Taking via View Rotation and Relation Reasoning for Embodied Reference Understanding

ECCV 2022arXiv

citations

Part2Object: Hierarchical Unsupervised 3D Instance Segmentation

ECCV 2024arXiv

citations

Rethinking Query-based Transformer for Continual Image Segmentation

CVPR 2025arXiv

citations

The Devil is in the Object Boundary: Towards Annotation-free Instance Segmentation using Foundation Models

ICLR 2024arXiv

citations

A Graph Dynamics Prior for Relational Inference

AAAI 2024arXiv

citations

Vision Function Layer in Multimodal LLMs

NEURIPS 2025arXiv

citations

Sim-DETR: Unlock DETR for Temporal Sentence Grounding

ICCV 2025arXiv

citations

Cheng Shi

papers (12)

Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator

Robust Reinforcement Learning via Adversarial training with Langevin Dynamics

Contrastive Grouping With Transformer for Referring Image Segmentation

EdaDet: Open-Vocabulary Object Detection Using Early Dense Alignment

LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models

Spatial and Visual Perspective-Taking via View Rotation and Relation Reasoning for Embodied Reference Understanding

Part2Object: Hierarchical Unsupervised 3D Instance Segmentation

Rethinking Query-based Transformer for Continual Image Segmentation

The Devil is in the Object Boundary: Towards Annotation-free Instance Segmentation using Foundation Models

A Graph Dynamics Prior for Relational Inference

Vision Function Layer in Multimodal LLMs

Sim-DETR: Unlock DETR for Temporal Sentence Grounding

papers (12)

Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator

Robust Reinforcement Learning via Adversarial training with Langevin Dynamics

Contrastive Grouping With Transformer for Referring Image Segmentation

EdaDet: Open-Vocabulary Object Detection Using Early Dense Alignment

LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models

Spatial and Visual Perspective-Taking via View Rotation and Relation Reasoning for Embodied Reference Understanding

Part2Object: Hierarchical Unsupervised 3D Instance Segmentation

Rethinking Query-based Transformer for Continual Image Segmentation

The Devil is in the Object Boundary: Towards Annotation-free Instance Segmentation using Foundation Models

A Graph Dynamics Prior for Relational Inference

Vision Function Layer in Multimodal LLMs

Sim-DETR: Unlock DETR for Temporal Sentence Grounding