AI.info

Kai Zhang

Explore Kai Zhang on AI.info.

• RankLLM: Weighted Ranking of LLMs by Quantifying Question Difficulty
• LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts
• P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling
• Beyond Affinity: A Benchmark of 1D, 2D, and 3D Methods Reveals Critical Trade-offs in Structure-Based Drug Design
• Layer-Order Inversion: Rethinking Latent Multi-Hop Reasoning in Large Language Models
• Self-Evaluation Unlocks Any-Step Text-to-Image Generation
• E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training
• Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety
• 1+1>2: A Synergistic Sparse and Low-Rank Compression Method for Large Language Models
• pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation
• Agent Learning via Early Experience