PPaperPicks

Deli Zhao

26 papers at tracked venues · 22 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. ParaFormer: A Generalized PageRank Graph Transformer for Graph Representation Learning
  2. Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors
  3. 2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining
  4. Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions
  5. Breaking the Memory Barrier of Contrastive Loss via Tile-Based Strategy
  6. Can Large Language Models Be Query Optimizer for Relational Databases?
  7. Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents
  8. CirT: Global Subseasonal-to-Seasonal Forecasting with Geometry-inspired Transformer
  9. EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?
  10. Equivariant and Invariant Message Passing for Global Subseasonal-to-seasonal Forecasting
  11. FineReason: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving
  12. GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning
  13. Large Language-Geometry Model: When LLM meets Equivariance
  14. MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra
  15. Non-stationary Equivariant Graph Neural Networks for Physical Dynamics Simulation
  16. ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning
  17. The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio
  18. Towards Scalable Spatial Intelligence Via 2D-To-3D Data Lifting
  19. Universally Invariant Learning in Equivariant GNNs
  20. VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM
  21. AnyDoor: Zero-shot Object-level Image Customization
  22. Latent Space Editing in Transformer-Based Flow Matching
  23. Lipschitz Singularities in Diffusion Models
  24. Space Group Constrained Crystal Generation
  25. Towards More Accurate Diffusion Model Acceleration with a Timestep Tuner
  26. UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Training