Jun Xiao

Towards Physically Executable 3D Gaussian for Embodied Navigation

SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models

TumorChain: Interleaved Multimodal Chain-of-Thought Reasoning for Traceable Clinical Tumor Analysis

VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models

Label-free GUI Grounding via Confidence-guided Negative Reinforcement Learning

Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generation

DPA-SGG: Dual Prompt Learning with Pseudo-Visual Augmentation for Open-Vocabulary Scene Graph Generation

AnyMS: Bottom-up Attention Decoupling for Layout-guided and Training-free Multi-subject Customization

HOW TO TRAIN YOUR DIFFUSION MODELS FOR FEW- SHOT CLASSIFICATION

CoMo: Compositional Motion Customization for Text-to-Video Generation

GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts

Learning Hierarchical Hyperbolic Embeddings for Compositional Zero-Shot Learning

LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization

UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning

Collaborative Hybrid Propagator for Temporal Misalignment in Audio-Visual Segmentation

Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning

Mind the Gap: Bridging Thought Leap for Improved Chain-of-Thought Tuning

HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation

Counterfactual Evolution of Multimodal Datasets via Visual Programming

Latent Score-Based Reweighting for Robust Classification on Imbalanced Tabular Data

Latent Score-Based Reweighting for Robust Classification on Imbalanced Tabular Data

Event-Customized Image Generation

Let LRMs Break Free from Overthinking via Self-Braking Tuning

Collaborative Hybrid Propagator for Temporal Misalignment in Audio-Visual Segmentation

Event-Customized Image Generation

TAGA: Self-supervised Learning for Template-free Animatable Gaussian Avatars

Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing