Yong Li

21

Papers

204

Total Citations

Papers (21)

GLOP: Learning Global Partition and Local Construction for Solving Large-Scale Routing Problems in Real-Time

AgentSquare: Automatic LLM Agent Search in Modular Design Space

Spatio-Temporal Few-Shot Learning via Diffusive Neural Network Generation

UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence

Diffusion Transformers as Open-World Spatiotemporal Foundation Models

NeurIPS 2025arXiv

Understanding Expressivity of GNN in Rule Learning

Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description length

Predicting the Energy Landscape of Stochastic Dynamical System via Physics-informed Self-supervised Learning

Efficient Long Context Fine-tuning with Chunk Flow

SAM-Aware Graph Prompt Reasoning Network for Cross-Domain Few-Shot Segmentation

A Large-scale Dataset and Benchmark for Commuting Origin-Destination Flow Generation

CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration

Masked Face Recognition with Generative-to-Discriminative Representations

Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification

Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers

PID-controlled Langevin Dynamics for Faster Sampling on Generative Models

NeurIPS 2025arXiv

Re-Attentional Controllable Video Diffusion Editing

Treasures in Discarded Weights for LLM Quantization

ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization

Social Physics Informed Diffusion Model for Crowd Simulation

Patch-Aware Sample Selection for Efficient Masked Image Modeling