Xin Eric Wang

Interleaved Vision-and-Language Generation via Generative Voken WACV 2026 What’s Missing in Vision-Language Models? Probing Their Struggles with Causal Order Reasoning EACL 2026 Agent S: An Open Agentic Framework that Uses Computers Like a Human ICLR 2025 Dynamic Evaluation for Oversensitivity in LLMs EMNLP 2025 EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing ICLR 2025 GUI-Bee: Align GUI Action Grounding to Novel Environments via Autonomous Exploration EMNLP 2025 Hidden in Plain Sight: Reasoning in Underspecified and Misspecified Scenarios for Multimodal LLMs EMNLP 2025 LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models NAACL 2025 MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos ICLR 2025 Multimodal Inconsistency Reasoning (MMIR): A New Benchmark for Multimodal Reasoning Models ACL 2025 Multimodal Situational Safety ICLR 2025 SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning EMNLP 2025 The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1 IJCNLP 2025 VLM4D: Towards Spatiotemporal Awareness in Vision Language Models ICCV 2025 Worse than Random? An Embarrassingly Simple Probing Evaluation of Large Multimodal Models in Medical VQA ACL 2025 Active Listening: Personalized Question Generation in Open-Domain Social Conversation with User Model Based Prompting EMNLP 2024 Multimodal Procedural Planning via Dual Text-Image Prompting EMNLP 2024 NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models ECCV 2024 Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding EMNLP 2024 SwapAnything: Enabling Arbitrary Object Swapping in Personalized Image Editing ECCV 2024 CUDA-GHR: Controllable Unsupervised Domain Adaptation for Gaze and Head Redirection WACV 2023 ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation ICML 2023 LayoutGPT: Compositional Visual Planning and Generation with Large Language Models NeurIPS 2023 LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation NeurIPS 2023 Neuro-Symbolic Procedural Planning with Commonsense Prompting ICLR 2023 Parameter-Efficient Model Adaptation for Vision Transformers AAAI 2023 PHOTOSWAP: Personalized Subject Swapping in Images NeurIPS 2023 Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis ICLR 2023 Compositional Temporal Grounding With Structured Variational Cross-Graph Correspondence Learning CVPR 2022 FedVLN: Privacy-Preserving Federated Vision-and-Language Navigation ECCV 2022 Language-Driven Artistic Style Transfer ECCV 2022 M3L: Language-Based Video Editing via Multi-Modal Multi-Level Transformers CVPR 2022 Understanding Instance-Level Impact of Fairness Constraints ICML 2022 Counterfactual Vision-and-Language Navigation via Adversarial Path Sampler ECCV 2020 Environment-agnostic Multitask Learning for Natural Language Grounded Navigation ECCV 2020