Jiaqi Wang

9 papers Beijing University of Posts and Telecommunications

• A Signed Graph Approach to Understanding and Mitigating Oversmoothing
• Fuse2Match: Training-Free Fusion of Flow, Diffusion, and Contrastive Models for Zero-Shot Semantic Matching
• HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance
• Learning Memory-Enhanced Improvement Heuristics for Flexible Job Shop Scheduling
• S$^2$M-Former: Spiking Symmetric Mixing Branchformer for Brain Auditory Attention Detection
• Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
• Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning
• Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought
• WearVQA: A Visual Question Answering Benchmark for Wearables in Egocentric Authentic Real-world scenarios