Qian Zhang
4 papers · Latest:
Machine Learning
Di-BiLPS: Denoising induced Bidirectional Latent-PDE-Solver under Sparse Observations
Di-BiLPS is a neural framework that solves PDEs efficiently under extremely sparse data, outperforming SOTA with zero-shot super-resolution.
2605.13790
Information RetrievalCAST: Modeling Semantic-Level Transitions for Complementary-Aware Sequential Recommendation
CAST models semantic-level transitions and injects LLM-verified priors to improve sequential recommendation by capturing true complementary relations.
2604.19414
Computer VisionRAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework
RAD-2 is a generator-discriminator framework that combines diffusion models and reinforcement learning for robust autonomous driving planning.
2604.15308
Computer VisionScal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction
Scal3R introduces a scalable test-time training approach for large-scale 3D reconstruction, using a neural global context to improve accuracy and consistency.
2604.08542
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.