AI.info

Jian Zhang

Explore Jian Zhang on AI.info.

• Beyond the Stability-Exploration Dilemma: Environmental Regularization for LLM Policy Optimization
• Historical Consensus: Preventing Posterior Collapse via Iterative Selection of Gaussian Mixture Priors
• When Shared Knowledge Hurts: Spectral Over-Accumulation in Model Merging
• Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD
• NVIDIA Nemotron 3: Efficient and Open Intelligence
• Toward Real-world Text Image Forgery Localization: Structured and Interpretable Data Synthesis
• Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment