Xin Eric Wang

Affiliations

University of California, Santa Cruz

papers

814

total citations

papers (12)

LayoutGPT: Compositional Visual Planning and Generation with Large Language Models

NEURIPS 2023arXiv

300

citations

Agent S: An Open Agentic Framework that Uses Computers Like a Human

ICLR 2025arXiv

107

citations

LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation

NEURIPS 2023arXiv

100

citations

Compositional Temporal Grounding With Structured Variational Cross-Graph Correspondence Learning

CVPR 2022arXiv

citations

Environment-agnostic Multitask Learning for Natural Language Grounded Navigation

ECCV 2020arXiv

citations

PHOTOSWAP: Personalized Subject Swapping in Images

NEURIPS 2023arXiv

citations

Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space

NEURIPS 2025arXiv

citations

MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos

ICLR 2025arXiv

citations

Xin Eric Wang

Affiliations

papers (12)

LayoutGPT: Compositional Visual Planning and Generation with Large Language Models

Agent S: An Open Agentic Framework that Uses Computers Like a Human

LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation

Compositional Temporal Grounding With Structured Variational Cross-Graph Correspondence Learning

Environment-agnostic Multitask Learning for Natural Language Grounded Navigation

PHOTOSWAP: Personalized Subject Swapping in Images

Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space

MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos

M3L: Language-Based Video Editing via Multi-Modal Multi-Level Transformers

FedVLN: Privacy-Preserving Federated Vision-and-Language Navigation

Language-Driven Artistic Style Transfer

Counterfactual Vision-and-Language Navigation via Adversarial Path Sampler

papers (12)

LayoutGPT: Compositional Visual Planning and Generation with Large Language Models

Agent S: An Open Agentic Framework that Uses Computers Like a Human

LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation

Compositional Temporal Grounding With Structured Variational Cross-Graph Correspondence Learning

Environment-agnostic Multitask Learning for Natural Language Grounded Navigation

PHOTOSWAP: Personalized Subject Swapping in Images

Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space

MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos

M3L: Language-Based Video Editing via Multi-Modal Multi-Level Transformers

FedVLN: Privacy-Preserving Federated Vision-and-Language Navigation

Language-Driven Artistic Style Transfer

Counterfactual Vision-and-Language Navigation via Adversarial Path Sampler