Zhi-Qi Cheng

Overcoming Joint Intractability with Lossless Hierarchical Speculative Decoding

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

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

MaxSup: Overcoming Representation Collapse in Label Smoothing

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

MaxSup: Fixing Label Smoothing for Improved Feature Representation

Prioritize Alignment in Dataset Distillation

Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarios

EIBench: Assessing the Emotion Interpretation ability of Vision Large Language Models