activity
20242026
collaborators

10 papers

cs.AI2026

HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions

Yifei Dong, Fengyi Wu, Qi He +9

Vision-and-Language Navigation (VLN) has been studied mainly in either discrete or continuous spaces, with little attention to dynamic, crowded environments. We present HA-VLN 2.0,…

cs.CV2026

GoViG: Goal-Conditioned Visual Navigation Instruction Generation via Multimodal Reasoning

Fengyi Wu, Yifei Dong, Yilong Dai +7

We introduce Goal-Conditioned Visual Navigation Instruction Generation (GoViG), a new task that aims to generate contextually coherent navigation instructions solely from egocentri…

cs.AI2026

Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresight

Yifei Dong, Fengyi Wu, Guangyu Chen +9

Enabling embodied agents to imagine future states is essential for robust and generalizable visual navigation. Yet, state-of-the-art systems typically rely on modular designs that…

cs.CV2025

Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmony

Chao Xu, Mingze Sun, Zhi-Qi Cheng +5

In this paper, we propose a novel framework, Combo, for harmonious co-speech holistic 3D human motion generation and efficient customizable adaption. In particular, we identify tha…

cs.CV2025

Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarios

Kai Wang, Zekai Li, Zhi-Qi Cheng +6

Dataset distillation has demonstrated strong performance on simple datasets like CIFAR, MNIST, and TinyImageNet but struggles to achieve similar results in more complex scenarios.…

cs.AI2025

MetaDesigner: Advancing Artistic Typography Through AI-Driven, User-Centric, and Multilingual WordArt Synthesis

Jun-Yan He, Zhi-Qi Cheng, Chenyang Li +11

MetaDesigner introduces a transformative framework for artistic typography synthesis, powered by Large Language Models (LLMs) and grounded in a user-centric design paradigm. Its fo…