AI.info

Jie Zhou

Explore Jie Zhou on AI.info.

• SM4RT: Learning Structured Motion Geometry for 4D Reconstruction
• How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoning
• Mimic Human Cognition, Master Multi-Image Reasoning: A Meta-Action Framework for Enhanced Visual Understanding
• ArrowGEV: Grounding Events in Video via Learning the Arrow of Time
• HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modeling
• SFTok: Bridging the Performance Gap in Discrete Tokenizers
• Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning
• SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder
• Astra: General Interactive World Model with Autoregressive Denoising
• Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generation
• MENTOR: A Metacognition-Driven Self-Evolution Framework for Uncovering and Mitigating Implicit Domain Risks in LLMs
• UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings
• Latent Diffusion Model without Variational Autoencoder
• Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning