Wei Wu

10 papers Peking University

• Beyond Node-Centric Modeling: Sketching Signed Networks with Simplicial Complexes
• DynaAct: Large Language Model Reasoning with Dynamic Action Spaces
• Generalized and Invariant Single-Neuron In-Vivo Activity Representation Learning
• Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access
• KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment
• Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
• RoboScape: Physics-informed Embodied World Model
• Theoretical Benefit and Limitation of Diffusion Language Model
• Towards Doctor-Like Reasoning: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients
• Understanding Parametric and Contextual Knowledge Reconciliation within Large Language Models