AI.info

Jiahao Li

Explore Jiahao Li on AI.info.

• Position: It is Time to Virtualize Foundation Models with a Self-evolving Operating System Layer
• Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
• InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training
• VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models
• Generative Latent Coding for Ultra-Low Bitrate Image Compression
• Single-step Diffusion-based Video Coding with Semantic-Temporal Guidance
• ReCAD: Reinforcement Learning Enhanced Parametric CAD Model Generation with Vision-Language Models
• Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding
• FireSentry: A Multi-Modal Spatio-temporal Benchmark Dataset for Fine-Grained Wildfire Spread Forecasting
• CoD: A Diffusion Foundation Model for Image Compression
• Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability Perspective
• SparseRM: A Lightweight Preference Modeling with Sparse Autoencoder