Trung Bui

papers

622

total citations

papers (13)

Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis

ICCV 2023arXiv

citations

Learning Navigational Visual Representations with Semantic Map Supervision

ICCV 2023arXiv

citations

Learning by Planning: Language-Guided Global Image Editing

CVPR 2021arXiv

citations

Scaling Up Video Summarization Pretraining with Large Language Models

CVPR 2024arXiv

citations

VSP: Diagnosing the Dual Challenges of Perception and Reasoning in Spatial Planning Tasks for MLLMs

ICCV 2025

citations

DynaSaur: Large Language Agents Beyond Predefined Actions

COLM 2025arXiv

citations

Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization

NEURIPS 2025arXiv

citations

Moment Detection in Long Tutorial Videos

ICCV 2023

citations

Yo’Chameleon: Personalized Vision and Language Generation

CVPR 2025

citations

Trung Bui

papers (13)

PhraseCut: Language-Based Image Segmentation in the Wild

Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models

Align and Attend: Multimodal Summarization With Dual Contrastive Losses

NoLiMa: Long-Context Evaluation Beyond Literal Matching

Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis

Learning Navigational Visual Representations with Semantic Map Supervision

Learning by Planning: Language-Guided Global Image Editing

Scaling Up Video Summarization Pretraining with Large Language Models

VSP: Diagnosing the Dual Challenges of Perception and Reasoning in Spatial Planning Tasks for MLLMs

DynaSaur: Large Language Agents Beyond Predefined Actions

Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization

Moment Detection in Long Tutorial Videos

Yo’Chameleon: Personalized Vision and Language Generation

papers (13)

PhraseCut: Language-Based Image Segmentation in the Wild

Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models

Align and Attend: Multimodal Summarization With Dual Contrastive Losses

NoLiMa: Long-Context Evaluation Beyond Literal Matching

Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis

Learning Navigational Visual Representations with Semantic Map Supervision

Learning by Planning: Language-Guided Global Image Editing

Scaling Up Video Summarization Pretraining with Large Language Models

VSP: Diagnosing the Dual Challenges of Perception and Reasoning in Spatial Planning Tasks for MLLMs

DynaSaur: Large Language Agents Beyond Predefined Actions

Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization

Moment Detection in Long Tutorial Videos

Yo’Chameleon: Personalized Vision and Language Generation