9 papers
CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking
Ruilong Ren, Songsheng Cheng, Yunpeng Zhou +9
Dynamic target tracking is essential for Unmanned Aerial Vehicles (UAVs) operating in complex urban environments, where both the target and the camera viewpoint change continuously…
CosFly-Track: A Large-Scale Multi-Modal Dataset for UAV Visual Tracking via Multi-Constraint Trajectory Optimization
Xiangyue Wang, Hanxuan Chen, Songsheng Cheng +7
Recent aerial vision-language navigation (VLN) datasets have grown rapidly, but they primarily address goal-oriented navigation to static destinations, leaving UAV visual tracking…
Leveraging Verifier-Based Reinforcement Learning in Image Editing
Hanzhong Guo, Jie Wu, Jie Liu +6
While Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm for text-to-image generation, its application to image editing remains largely unexplored. A k…
CosFly: Plan in the Matrix, Fly in the World
Hanxuan Chen, Xiangyue Wang, Songsheng Cheng +8
We present CosFly, a box-structured planning and multimodal simulation pipeline for aerial tracking, together with CosFly-Track, a large-scale UAV dataset for dynamic target tracki…
Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
Meng Lou, Hanzhong Guo, Linwei Chen +1
Recent studies suggest that Reinforcement Fine-Tuning (RFT) is inherently more resilient to catastrophic forgetting than Supervised Fine-Tuning (SFT). However, whether RFT (e.g., G…
Decomposing Subject-Driven Image Generation via Intermediate Structural Prediction
Hanzhong Guo, Yizhou Yu
Subject-driven text-to-image generation still struggles to preserve high-frequency identity details such as logos, patterns, and text. Existing methods typically operate directly i…
Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms
Muyang He, Hanzhong Guo, Junxiong Lin +1
The rapid evolution of video generation has enabled models to simulate complex physical dynamics and long-horizon causalities, positioning them as potential world simulators. Howev…
RewardDance: Reward Scaling in Visual Generation
Jie Wu, Yu Gao, Zilyu Ye +9
Reward Models (RMs) are critical for improving generation models via Reinforcement Learning (RL), yet the RM scaling paradigm in visual generation remains largely unexplored. It pr…
UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation
Qin Guo, Ailing Zeng, Dongxu Yue +7
Although significant advancements have been achieved in the progress of keypoint-guided Text-to-Image diffusion models, existing mainstream keypoint-guided models encounter challen…