Shiming Xiang

Beyond Next-Token Alignment: Distilling Multimodal Large Language Models via Token Interactions

Continuous Speculative Decoding for Autoregressive Image Generation

MNO: Multiscale Neural Operator for Computational Fluid Dynamics with 3D Point Cloud Data

Panorama Generation with Multiple Custom Background Objects

Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization

UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation

Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering

AddressVLM: Cross-view Alignment Tuning for Image Address Localization using Large Vision-Language Models

Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger

AVESFormer: Efficient Transformer Design for Real-Time Audio-Visual Segmentation