AI.info

Hongsheng Li

Explore Hongsheng Li on AI.info.

• InterleaveThinker: Reinforcing Agentic Interleaved Generation
• LMGenDrive: Bridging Multimodal Understanding and Generative World Modeling for End-to-End Driving
• InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing
• MetaphorStar: Image Metaphor Understanding and Reasoning with End-to-End Visual Reinforcement Learning
• PromptRL: Prompt Matters in RL for Flow-Based Image Generation
• SlidesGen-Bench: Evaluating Slides Generation via Computational and Quantitative Metrics
• DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving
• DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation
• Optimizing Distributional Geometry Alignment with Optimal Transport for Generative Dataset Distillation
• AIA: Rethinking Architecture Decoupling Strategy In Unified Multimodal Model
• Rethinking Long-tailed Dataset Distillation: A Uni-Level Framework with Unbiased Recovery and Relabeling
• Neighbor GRPO: Contrastive ODE Policy Optimization Aligns Flow Models
• Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigation
• ProteinAE: Protein Diffusion Autoencoders for Structure Encoding
• BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception
• NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints