Zhengzhong Tu

Agent Banana: High-Fidelity Image Editing with Agentic Thinking and Tooling

arXiv 2026

PISCO: Precise Video Instance Insertion with Sparse Control

arXiv 2026

The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics

arXiv 2026

Digital Twin AI: Opportunities and Challenges from Large Language Models to World Models

arXiv 2026

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

arXiv 2025

Generative AI for Autonomous Driving: Frontiers and Opportunities

arXiv 2025

DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization

arXiv 2025

On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective

arXiv 2025

LangCoop: Collaborative Driving with Language

arXiv 2025

NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results

arXiv 2025

LLMs Can Get "Brain Rot"!

arXiv 2025

4KAgent: Agentic Any Image to 4K Super-Resolution

arXiv 2025

UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving

ICCV 2025

Complex LLM Planning via Automated Heuristics Discovery

arXiv 2025

Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization

arXiv 2025

Can Large Vision Language Models Read Maps Like a Human?

arXiv 2025

Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs

arXiv 2025

MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning

arXiv 2025

Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models

arXiv 2024

AIS 2024 Challenge on Video Quality Assessment of User-Generated Content: Methods and Results

arXiv 2024

OpenEMMA: Open-Source Multimodal Model for End-to-End Autonomous Driving

arXiv 2024

AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving

arXiv 2024

Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing

CVPR 2025 1