Zihan Wang

OpenReview

Affiliations

Northwestern UniversityUniversity of California San Diego

papers

2,251

total citations

papers (18)

Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

CVPR 2025arXiv

917

citations

CogAgent: A Visual Language Model for GUI Agents

CVPR 2024arXiv

629

citations

MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback

ICLR 2024arXiv

260

citations

GridMM: Grid Memory Map for Vision-and-Language Navigation

ICCV 2023arXiv

111

citations

PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection

CVPR 2023arXiv

citations

KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation

CVPR 2023arXiv

citations

Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation

CVPR 2024arXiv

citations

Re-thinking Temporal Search for Long-Form Video Understanding

CVPR 2025arXiv

citations

Implicit bias of SGD in $L_2$-regularized linear DNNs: One-way jumps from high to low rank

ICLR 2024

citations

Reducing Tool Hallucination via Reliability Alignment

ICML 2025arXiv

citations

Multi-scale Dynamic and Hierarchical Relationship Modeling for Facial Action Units Recognition

CVPR 2024arXiv

citations

g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks

CVPR 2025arXiv

citations

Modeling Cell Dynamics and Interactions with Unbalanced Mean Field Schrödinger Bridge

NEURIPS 2025arXiv

citations

Variational Regularized Unbalanced Optimal Transport: Single Network, Least Action

NEURIPS 2025arXiv

citations

MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion

ICCV 2025arXiv

citations

Auxiliary Prompt Tuning of Vision-Language Models for Few-Shot Out-of-Distribution Detection

ICCV 2025

citations

Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback

NEURIPS 2023

citations

M$^4$I: Multi-modal Models Membership Inference

NEURIPS 2022

citations