Xue Yang

Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization

SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence

MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization

Object Fidelity Diffusion for Remote Sensing Image Generation

SPWOOD: Sparse Partial Weakly-Supervised Oriented Object Detection

Interleave-VLA: Enhancing Robot Manipulation with Image-Text Interleaved Instructions

GLEAM: Learning to Match and Explain in Cross-View Geo-Localization

Progressive Vision-Language Alignment via LLM-based Embedder

Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space

InstructSAM: A Training-free Framework for Instruction-Oriented Remote Sensing Object Recognition

PointOBB-v2: Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object Detection

OPMapper: Enhancing Open-Vocabulary Semantic Segmentation with Multi-Guidance Information

GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data

Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)

Maintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-tuning

Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training