Zhi Gao

When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations

Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds

Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation

Multi-Step Reasoning for Embodied Question Answering via Tool Augmentation

STVG-R1: Incentivizing Instance-Level Reasoning and Grounding in Videos via Reinforcement Learning

VUDG: A Dataset for Video Understanding Domain Generalization

GUI Knowledge Bench: Revealing the Knowledge Gap Behind VLM Failures in GUI Tasks

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Augmentations and Constraints

Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning

Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage

Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning

MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge

Geometry-aware Distance Measure for Diverse Hierarchical Structures in Hyperbolic Spaces