9 papers
Think Like a Pilot: Fine-Grained Long-Horizon UAV Navigation
Xiangyi Zheng, Xiangyu Wang, Qinan Liao +6
Language-guided UAV agents must execute long-horizon semantic instructions while producing smooth, physically feasible continuous flight commands, yet existing Vision-Language Navi…
MC#: Mixture Compressor for Mixture-of-Experts Large Models
Wei Huang, Yue Liao, Yukang Chen +6
Mixture-of-Experts (MoE) effectively scales large language models (LLMs) and vision-language models (VLMs) by increasing capacity through sparse activation. However, preloading all…
Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs
Zitian Wang, Yue Liao, Kang Rong +3
Preference alignment has emerged as an effective strategy to enhance the performance of Multimodal Large Language Models (MLLMs) following supervised fine-tuning. While existing pr…
Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency
Hongyu Li, Songhao Han, Yue Liao +4
Understanding real-world videos with complex semantics and long temporal dependencies remains a fundamental challenge in computer vision. Recent progress in multimodal large langua…
UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning
Xiangyu Wang, Donglin Yang, Yue Liao +5
Unmanned Aerial Vehicles (UAVs) are evolving into language-interactive platforms, enabling more intuitive forms of human-drone interaction. While prior works have primarily focused…
TopV-Nav: Unlocking the Top-View Spatial Reasoning Potential of MLLM for Zero-shot Object Navigation
Linqing Zhong, Chen Gao, Zihan Ding +5
The Zero-Shot Object Navigation (ZSON) task requires embodied agents to find a previously unseen object by navigating in unfamiliar environments. Such a goal-oriented exploration h…